aboutsummaryrefslogtreecommitdiff
path: root/tests
diff options
context:
space:
mode:
authorSteve Bennett <steveb@workware.net.au>2010-10-16 21:07:06 +1000
committerSteve Bennett <steveb@workware.net.au>2010-10-20 10:30:34 +1000
commit9fcb8099151969bc148ecd69934ee061b77eb2bd (patch)
tree7d988c45f87e63b5dfe105c554315f2fd3a5aad4 /tests
parentdad7d138ad9d14cc9af7ec2139ac860c4bdf9f27 (diff)
downloadjimtcl-9fcb8099151969bc148ecd69934ee061b77eb2bd.zip
jimtcl-9fcb8099151969bc148ecd69934ee061b77eb2bd.tar.gz
jimtcl-9fcb8099151969bc148ecd69934ee061b77eb2bd.tar.bz2
Fix some outlier issues with regexp/regsub
Use number of paren expressions with regexp -inline Fix a problem with regexp -start and an anchored search Fix regexp -inline -indices Fix regexp matching with an empty pattern (e.g. ^) Fix some cases where regsub -all did not return all results Fix some regsub cases with an empty pattern Signed-off-by: Steve Bennett <steveb@workware.net.au>
Diffstat (limited to 'tests')
-rw-r--r--tests/jim.test575
-rw-r--r--tests/regexp.test649
2 files changed, 642 insertions, 582 deletions
diff --git a/tests/jim.test b/tests/jim.test
index 2ba5faf..b414c25 100644
--- a/tests/jim.test
+++ b/tests/jim.test
@@ -3574,581 +3574,6 @@ test lrange-2.4 {error conditions} {
#} {1 {unmatched open brace in list}}
################################################################################
-# REGEXP and REGSUB
-################################################################################
-
-test regexp-1.1 {basic regexp operation} {
- regexp ab*c abbbc
-} {1}
-
-test regexp-1.2 {basic regexp operation} {
- regexp ab*c ac
-} {1}
-
-test regexp-1.3 {basic regexp operation} {
- regexp ab*c ab
-} {0}
-
-test regexp-1.4 {basic regexp operation} {
- regexp -- -gorp abc-gorpxxx
-} {1}
-
-test regexp-1.5 {basic regexp operation} {
- regexp {^([^ ]*)[ ]*([^ ]*)} "" a
-} {1}
-
-# This null case doesn't work with some regex libraries
-# No great loss
-#test regexp-1.6 {basic regexp operation} {
-# list [catch {regexp {} abc} msg] $msg
-#} {0 1}
-
-test regexp-2.1 {getting substrings back from regexp} {
- set foo {}
- list [regexp ab*c abbbbc foo] $foo
-} {1 abbbbc}
-
-test regexp-2.2 {getting substrings back from regexp} {
- set foo {}
- set f2 {}
- list [regexp a(b*)c abbbbc foo f2] $foo $f2
-} {1 abbbbc bbbb}
-
-test regexp-2.3 {getting substrings back from regexp} {
- set foo {}
- set f2 {}
- list [regexp a(b*)(c) abbbbc foo f2] $foo $f2
-} {1 abbbbc bbbb}
-
-test regexp-2.4 {getting substrings back from regexp} {
- set foo {}
- set f2 {}
- set f3 {}
- list [regexp a(b*)(c) abbbbc foo f2 f3] $foo $f2 $f3
-} {1 abbbbc bbbb c}
-
-test regexp-2.5 {getting substrings back from regexp} {
- 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 regexp-2.6 {getting substrings back from regexp} {
- 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 regexp-2.7 {getting substrings back from regexp} {
- 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 regexp-2.8 {getting substrings back from regexp} {
- set match {}
- list [regexp {^a*b} aaaab match] $match
-} {1 aaaab}
-
-test regexp-3.1 {-indices option to regexp} {
- set foo {}
- list [regexp -indices ab*c abbbbc foo] $foo
-} {1 {0 5}}
-
-test regexp-3.2 {-indices option to regexp} {
- set foo {}
- set f2 {}
- list [regexp -indices a(b*)c abbbbc foo f2] $foo $f2
-} {1 {0 5} {1 4}}
-
-test regexp-3.3 {-indices option to regexp} {
- set foo {}
- set f2 {}
- list [regexp -indices a(b*)(c) abbbbc foo f2] $foo $f2
-} {1 {0 5} {1 4}}
-
-test regexp-3.4 {-indices option to regexp} {
- 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 regexp-3.5 {-indices option to regexp} {
- 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 regexp-3.6 {getting substrings back from regexp} {
- 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 regexp-3.7 {getting substrings back from regexp} {
- 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 regexp-4.1 {-nocase option to regexp} {
- regexp -nocase foo abcFOo
-} {1}
-
-test regexp-4.2 {-nocase option to regexp} {
- 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 regexp-4.3 {-nocase option to regexp} {
- regexp -nocase FOo abcFOo
-} {1}
-
-test regexp-4.4 {case conversion in regexp} {
- set x abcdefghijklmnopqrstuvwxyz1234567890abcdefghijklmnopqrstuvwxyz1234567890abcdefghijklmnopqrstuvwxyz1234567890abcdefghijklmnopqrstuvwxyz1234567890abcdefghijklmnopqrstuvwxyz1234567890abcdefghijklmnopqrstuvwxyz1234567890abcdefghijklmnopqrstuvwxyz1234567890abcdefghijklmnopqrstuvwxyz1234567890abcdefghijklmnopqrstuvwxyz1234567890abcdefghijklmnopqrstuvwxyz1234567890abcdefghijklmnopqrstuvwxyz1234567890abcdefghijklmnopqrstuvwxyz1234567890
- list [regexp -nocase $x $x foo] $foo
-} {1 abcdefghijklmnopqrstuvwxyz1234567890abcdefghijklmnopqrstuvwxyz1234567890abcdefghijklmnopqrstuvwxyz1234567890abcdefghijklmnopqrstuvwxyz1234567890abcdefghijklmnopqrstuvwxyz1234567890abcdefghijklmnopqrstuvwxyz1234567890abcdefghijklmnopqrstuvwxyz1234567890abcdefghijklmnopqrstuvwxyz1234567890abcdefghijklmnopqrstuvwxyz1234567890abcdefghijklmnopqrstuvwxyz1234567890abcdefghijklmnopqrstuvwxyz1234567890abcdefghijklmnopqrstuvwxyz1234567890}
-
-test regexp-5.1 {exercise cache of compiled expressions} {
- regexp .*a b
- regexp .*b c
- regexp .*c d
- regexp .*d e
- regexp .*e f
- regexp .*a bbba
-} {1}
-
-test regexp-5.2 {exercise cache of compiled expressions} {
- regexp .*a b
- regexp .*b c
- regexp .*c d
- regexp .*d e
- regexp .*e f
- regexp .*b xxxb
-} {1}
-
-test regexp-5.3 {exercise cache of compiled expressions} {
- regexp .*a b
- regexp .*b c
- regexp .*c d
- regexp .*d e
- regexp .*e f
- regexp .*c yyyc
-} {1}
-
-test regexp-5.4 {exercise cache of compiled expressions} {
- regexp .*a b
- regexp .*b c
- regexp .*c d
- regexp .*d e
- regexp .*e f
- regexp .*d 1d
-} {1}
-
-test regexp-5.5 {exercise cache of compiled expressions} {
- regexp .*a b
- regexp .*b c
- regexp .*c d
- regexp .*d e
- regexp .*e f
- regexp .*e xe
-} {1}
-
-test regexp-6.1 {regexp errors} {
- list [catch {regexp a} msg] $msg
-} {1 {wrong # args: should be "regexp ?-nocase? ?-line? ?-indices? ?-start offset? ?-all? ?-inline? ?--? exp string ?matchVar? ?subMatchVar ...?"}}
-
-test regexp-6.2 {regexp errors} {
- list [catch {regexp -nocase a} msg] $msg
-} {1 {wrong # args: should be "regexp ?-nocase? ?-line? ?-indices? ?-start offset? ?-all? ?-inline? ?--? exp string ?matchVar? ?subMatchVar ...?"}}
-
-test regexp-6.3 {regexp errors} {
- list [catch {regexp -gorp a} msg] $msg
-} {1 {wrong # args: should be "regexp ?-nocase? ?-line? ?-indices? ?-start offset? ?-all? ?-inline? ?--? exp string ?matchVar? ?subMatchVar ...?"}}
-
-test regexp-6.4 {regexp errors} {
- catch {regexp a( b} msg
-} {1}
-
-test regexp-6.5 {regexp errors} {
- catch {regexp a( b} msg
-} {1}
-
-test regexp-6.6 {regexp errors} {
- 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 regexp-6.7 {regexp errors} {
- list [catch {regexp (x)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.) xyzzy} msg] $msg
-} {0 0}
-
-test regexp-6.8 {regexp errors} {
- catch {unset f1}
- set f1 44
- list [catch {regexp abc abc f1(f2)} msg] $msg
-} {1 {can't set "f1(f2)": variable isn't array}}
-
-test regexp-6.9 {regexp errors, -start bad int check} {
- list [catch {regexp -start bogus {^$} {}} msg] $msg
-} {1 {expected integer but got "bogus"}}
-
-test regexp-7.1 {basic regsub operation} {
- list [regsub aa+ xaxaaaxaa 111&222 foo] $foo
-} {1 xax111aaa222xaa}
-
-test regexp-7.2 {basic regsub operation} {
- list [regsub aa+ aaaxaa &111 foo] $foo
-} {1 aaa111xaa}
-
-test regexp-7.3 {basic regsub operation} {
- list [regsub aa+ xaxaaa 111& foo] $foo
-} {1 xax111aaa}
-
-test regexp-7.4 {basic regsub operation} {
- list [regsub aa+ aaa 11&2&333 foo] $foo
-} {1 11aaa2aaa333}
-
-test regexp-7.5 {basic regsub operation} {
- list [regsub aa+ xaxaaaxaa &2&333 foo] $foo
-} {1 xaxaaa2aaa333xaa}
-
-test regexp-7.6 {basic regsub operation} {
- list [regsub aa+ xaxaaaxaa 1&22& foo] $foo
-} {1 xax1aaa22aaaxaa}
-
-test regexp-7.7 {basic regsub operation} {
- list [regsub a(a+) xaxaaaxaa {1\122\1} foo] $foo
-} {1 xax1aa22aaxaa}
-
-test regexp-7.8 {basic regsub operation} {
- list [regsub a(a+) xaxaaaxaa {1\\\122\1} foo] $foo
-} {1 {xax1\aa22aaxaa}}
-
-test regexp-7.9 {basic regsub operation} {
- list [regsub a(a+) xaxaaaxaa {1\\122\1} foo] $foo
-} {1 {xax1\122aaxaa}}
-
-test regexp-7.10 {basic regsub operation} {
- list [regsub a(a+) xaxaaaxaa {1\\&\1} foo] $foo
-} {1 {xax1\aaaaaxaa}}
-
-test regexp-7.11 {basic regsub operation} {
- list [regsub a(a+) xaxaaaxaa {1\&\1} foo] $foo
-} {1 xax1&aaxaa}
-
-test regexp-7.12 {basic regsub operation} {
- list [regsub a(a+) xaxaaaxaa {\1\1\1\1&&} foo] $foo
-} {1 xaxaaaaaaaaaaaaaaxaa}
-
-test regexp-7.13 {basic regsub operation} {
- set foo xxx
- list [regsub abc xyz 111 foo] $foo
-} {0 xyz}
-
-test regexp-7.14 {basic regsub operation} {
- set foo xxx
- list [regsub ^ xyz "111 " foo] $foo
-} {1 {111 xyz}}
-
-test regexp-7.15 {basic regsub operation} {
- set foo xxx
- list [regsub -- -foo abc-foodef "111 " foo] $foo
-} {1 {abc111 def}}
-
-test regexp-7.16 {basic regsub operation} {
- set foo xxx
- list [regsub x "" y foo] $foo
-} {0 {}}
-
-test regexp-8.1 {case conversion in regsub} {
- list [regsub -nocase a(a+) xaAAaAAay & foo] $foo
-} {1 xaAAaAAay}
-
-test regexp-8.2 {case conversion in regsub} {
- list [regsub -nocase a(a+) xaAAaAAay & foo] $foo
-} {1 xaAAaAAay}
-
-test regexp-8.3 {case conversion in regsub} {
- set foo 123
- list [regsub a(a+) xaAAaAAay & foo] $foo
-} {0 xaAAaAAay}
-
-test regexp-8.4 {case conversion in regsub} {
- set foo 123
- list [regsub -nocase a CaDE b foo] $foo
-} {1 CbDE}
-
-test regexp-8.5 {case conversion in regsub} {
- set foo 123
- list [regsub -nocase XYZ CxYzD b foo] $foo
-} {1 CbD}
-
-test regexp-8.6 {case conversion in regsub} {
- 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 regexp-9.1 {-all option to regsub} {
- set foo 86
- list [regsub -all x+ axxxbxxcxdx |&| foo] $foo
-} {4 a|xxx|b|xx|c|x|d|x|}
-
-test regexp-9.2 {-all option to regsub} {
- set foo 86
- list [regsub -nocase -all x+ aXxXbxxcXdx |&| foo] $foo
-} {4 a|XxX|b|xx|c|X|d|x|}
-
-test regexp-9.3 {-all option to regsub} {
- set foo 86
- list [regsub x+ axxxbxxcxdx |&| foo] $foo
-} {1 a|xxx|bxxcxdx}
-
-test regexp-9.4 {-all option to regsub} {
- set foo 86
- list [regsub -all bc axxxbxxcxdx |&| foo] $foo
-} {0 axxxbxxcxdx}
-
-test regexp-9.5 {-all option to regsub} {
- set foo xxx
- list [regsub -all node "node node more" yy foo] $foo
-} {2 {yy yy more}}
-
-test regexp-9.6 {-all option to regsub} {
- set foo xxx
- list [regsub -all ^ xxx 123 foo] $foo
-} {1 123xxx}
-
-test regexp-10.2 {newline sensitivity in regsub} {
- set foo xxx
- list [regsub -line {^a.*b$} "dabc\naxyb\n" 123 foo] $foo
-} {1 {dabc
-123
-}}
-
-test regexp-10.3 {newline sensitivity in regsub} {
- set foo xxx
- list [regsub -line {^a.*b$} "dabc\naxyb\nxb" 123 foo] $foo
-} {1 {dabc
-123
-xb}}
-
-test regexp-11.1 {regsub errors} {
- list [catch {regsub a b} msg] $msg
-} {1 {wrong # args: should be "regsub ?-nocase? ?-all? ?-line? ?-start offset? ?--? exp string subSpec ?varName?"}}
-
-test regexp-11.2 {regsub errors} {
- list [catch {regsub -nocase a b} msg] $msg
-} {1 {wrong # args: should be "regsub ?-nocase? ?-all? ?-line? ?-start offset? ?--? exp string subSpec ?varName?"}}
-
-test regexp-11.3 {regsub errors} {
- list [catch {regsub -nocase -all a b} msg] $msg
-} {1 {wrong # args: should be "regsub ?-nocase? ?-all? ?-line? ?-start offset? ?--? exp string subSpec ?varName?"}}
-
-test regexp-11.4 {regsub errors} {
- list [catch {regsub a b c d e f} msg] $msg
-} {1 {wrong # args: should be "regsub ?-nocase? ?-all? ?-line? ?-start offset? ?--? exp string subSpec ?varName?"}}
-
-test regexp-11.5 {regsub errors} {
- list [catch {regsub -gorp a b c} msg] $msg
-} {1 {wrong # args: should be "regsub ?-nocase? ?-all? ?-line? ?-start offset? ?--? exp string subSpec ?varName?"}}
-
-test regexp-11.6 {regsub errors} {
- catch {regsub -nocase a( b c d} msg
-} {1}
-
-test regexp-11.7 {regsub errors} {
- catch {unset f1}
- set f1 44
- list [catch {regsub -nocase aaa aaa xxx f1(f2)} msg] $msg
-} {1 {can't set "f1(f2)": variable isn't array}}
-
-test regexp-11.8 {regsub errors, -start bad int check} {
- list [catch {regsub -start bogus pattern string rep var} msg] $msg
-} {1 {expected integer but got "bogus"}}
-
-test regexp-12.1 {Tcl_RegExpExec: large number of subexpressions} {
- 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 regexp-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 regexp-14.1 {CompileRegexp: regexp cache} {
- 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 regexp-14.2 {CompileRegexp: regexp cache, different flags} {
- 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 regexp-15.1 {regexp -start} {
- catch {unset x}
- list [regexp -start -10 {[0-9]} 1abc2de3 x] $x
-} {1 1}
-
-test regexp-15.2 {regexp -start} {
- catch {unset x}
- list [regexp -start 2 {[0-9]} 1abc2de3 x] $x
-} {1 2}
-
-test regexp-15.3 {regexp -start} {
- catch {unset x}
- list [regexp -start 4 {[0-9]} 1abc2de3 x] $x
-} {1 2}
-
-test regexp-15.4 {regexp -start} {
- catch {unset x}
- list [regexp -start 5 {[0-9]} 1abc2de3 x] $x
-} {1 3}
-
-test regexp-15.5 {regexp -start, over end of string} {
- catch {unset x}
- list [regexp -start [string length 1abc2de3] {[0-9]} 1abc2de3 x] [info exists x]
-} {0 0}
-
-test regexp-15.6 {regexp -start, loss of ^$ behavior} {
- list [regexp -start 2 {^$} {}]
-} {1}
-
-test regexp-16.1 {regsub -start} {
- catch {unset x}
- list [regsub -all -start 2 {[0-9]} a1b2c3d4e5 {/&} x] $x
-} {4 a1b/2c/3d/4e/5}
-
-test regexp-16.2 {regsub -start} {
- catch {unset x}
- list [regsub -all -start -25 {z} hello {/&} x] $x
-} {0 hello}
-
-test regexp-16.3 {regsub -start} {
- catch {unset x}
- list [regsub -all -start 3 {z} hello {/&} x] $x
-} {0 hello}
-
-test regexp-17.1 {regexp -inline} {
- regexp -inline b ababa
-} {b}
-
-test regexp-17.2 {regexp -inline} {
- regexp -inline (b) ababa
-} {b b}
-
-test regexp-17.3 {regexp -inline -indices} {
- regexp -inline -indices (b) ababa
-} {{1 1} {1 1}}
-
-test regexp-17.4 {regexp -inline} {
- regexp -inline {[[:alnum:]_]([0-9]+)[[:alnum:]_]} " hello 23 there456def "
-} {e456d 456}
-
-test regexp-17.5 {regexp -inline no matches} {
- regexp -inline {[[:alnum:]_]([0-9]+)[[:alnum:]_]} ""
-} {}
-
-test regexp-17.6 {regexp -inline no matches} {
- regexp -inline hello goodbye
-} {}
-
-test regexp-17.7 {regexp -inline, no matchvars allowed} {
- list [catch {regexp -inline b abc match} msg] $msg
-} {1 {regexp match variables not allowed when using -inline}}
-
-test regexp-18.1 {regexp -all} {
- regexp -all b bbbbb
-} {5}
-
-test regexp-18.2 {regexp -all} {
- regexp -all b abababbabaaaaaaaaaab
-} {6}
-
-test regexp-18.3 {regexp -all -inline} {
- regexp -all -inline b abababbabaaaaaaaaaab
-} {b b b b b b}
-
-test regexp-18.4 {regexp -all -inline} {
- regexp -all -inline {[[:alnum:]_]([[:alnum:]_])} abcdefg
-} {ab b cd d ef f}
-
-test regexp-18.5 {regexp -all -inline} {
- regexp -all -inline {[[:alnum:]_]([[:alnum:]_])$} abcdefg
-} {fg g}
-
-test regexp-18.6 {regexp -all -inline} {
- regexp -all -inline {[0-9]+} 10:20:30:40
-} {10 20 30 40}
-
-test regexp-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 regexp-18.8 {regexp -all} {
- # This should not cause an infinite loop
- regexp -all -inline {a*} a
-} {a}
-
-test regexp-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 regexp-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 regexp-18.11 {regexp -all} {
- regexp -all -inline {^a} aaaa
-} {a}
-
-test regexp-19.1 {regsub null replacement} {
- regsub -all {@} {@hel@lo@} "\0a\0" result
- list $result [string length $result]
-} "\0a\0hel\0a\0lo\0a\0 14"
-
-
-################################################################################
# RANGE
################################################################################
diff --git a/tests/regexp.test b/tests/regexp.test
index df8189f..82a6c67 100644
--- a/tests/regexp.test
+++ b/tests/regexp.test
@@ -1,7 +1,647 @@
+# 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: regexp.test,v 1.30.2.1 2008/08/21 23:19:06 hobbs Exp $
+
source testing.tcl
package-or-skip regexp
-test regexp-1.1 {effect of caching} {
+catch {unset foo}
+test regexp-1.1 {basic regexp operation} {
+ regexp ab*c abbbc
+} 1
+test regexp-1.2 {basic regexp operation} {
+ regexp ab*c ac
+} 1
+test regexp-1.3 {basic regexp operation} {
+ regexp ab*c ab
+} 0
+test regexp-1.4 {basic regexp operation} {
+ regexp -- -gorp abc-gorpxxx
+} 1
+test regexp-1.5 {basic regexp operation} {
+ regexp {^([^ ]*)[ ]*([^ ]*)} "" a
+} 1
+#test regexp-1.6 {basic regexp operation} {
+# list [catch {regexp {} abc} msg] $msg
+#} {0 1}
+#test regexp-1.7 {regexp utf compliance} {
+# # if not UTF-8 aware, result is "0 1"
+# 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 regexp-2.1 {getting substrings back from regexp} {
+ set foo {}
+ list [regexp ab*c abbbbc foo] $foo
+} {1 abbbbc}
+test regexp-2.2 {getting substrings back from regexp} {
+ set foo {}
+ set f2 {}
+ list [regexp a(b*)c abbbbc foo f2] $foo $f2
+} {1 abbbbc bbbb}
+test regexp-2.3 {getting substrings back from regexp} {
+ set foo {}
+ set f2 {}
+ list [regexp a(b*)(c) abbbbc foo f2] $foo $f2
+} {1 abbbbc bbbb}
+test regexp-2.4 {getting substrings back from regexp} {
+ set foo {}
+ set f2 {}
+ set f3 {}
+ list [regexp a(b*)(c) abbbbc foo f2 f3] $foo $f2 $f3
+} {1 abbbbc bbbb c}
+test regexp-2.5 {getting substrings back from regexp} {
+ 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 regexp-2.6 {getting substrings back from regexp} {
+ 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 regexp-2.7 {getting substrings back from regexp} {
+ 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 regexp-2.8 {getting substrings back from regexp} {
+ set match {}
+ list [regexp {^a*b} aaaab match] $match
+} {1 aaaab}
+test regexp-2.9 {getting substrings back from regexp} {
+ set foo {}
+ set f2 {}
+ list [regexp f\352te(b*)c f\352tebbbbc foo f2] $foo $f2
+} [list 1 f\352tebbbbc bbbb]
+test regexp-2.10 {getting substrings back from regexp} {
+ set foo {}
+ set f2 {}
+ list [regexp f\352te(b*)c eff\352tebbbbc foo f2] $foo $f2
+} [list 1 f\352tebbbbc bbbb]
+
+test regexp-3.1 {-indices option to regexp} {
+ set foo {}
+ list [regexp -indices ab*c abbbbc foo] $foo
+} {1 {0 5}}
+test regexp-3.2 {-indices option to regexp} {
+ set foo {}
+ set f2 {}
+ list [regexp -indices a(b*)c abbbbc foo f2] $foo $f2
+} {1 {0 5} {1 4}}
+test regexp-3.3 {-indices option to regexp} {
+ set foo {}
+ set f2 {}
+ list [regexp -indices a(b*)(c) abbbbc foo f2] $foo $f2
+} {1 {0 5} {1 4}}
+test regexp-3.4 {-indices option to regexp} {
+ 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 regexp-3.5 {-indices option to regexp} {
+ 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 regexp-3.6 {getting substrings back from regexp} {
+ 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 regexp-3.7 {getting substrings back from regexp} {
+ 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 regexp-4.1 {-nocase option to regexp} {
+ regexp -nocase foo abcFOo
+} 1
+test regexp-4.2 {-nocase option to regexp} {
+ 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 regexp-4.3 {-nocase option to regexp} {
+ regexp -nocase FOo abcFOo
+} 1
+set x abcdefghijklmnopqrstuvwxyz1234567890
+set x $x$x$x$x$x$x$x$x$x$x$x$x
+test regexp-4.4 {case conversion in regexp} {
+ list [regexp -nocase $x $x foo] $foo
+} "1 $x"
+catch {unset x}
+
+test regexp-5.1 {exercise cache of compiled expressions} {
+ regexp .*a b
+ regexp .*b c
+ regexp .*c d
+ regexp .*d e
+ regexp .*e f
+ regexp .*a bbba
+} 1
+test regexp-5.2 {exercise cache of compiled expressions} {
+ regexp .*a b
+ regexp .*b c
+ regexp .*c d
+ regexp .*d e
+ regexp .*e f
+ regexp .*b xxxb
+} 1
+test regexp-5.3 {exercise cache of compiled expressions} {
+ regexp .*a b
+ regexp .*b c
+ regexp .*c d
+ regexp .*d e
+ regexp .*e f
+ regexp .*c yyyc
+} 1
+test regexp-5.4 {exercise cache of compiled expressions} {
+ regexp .*a b
+ regexp .*b c
+ regexp .*c d
+ regexp .*d e
+ regexp .*e f
+ regexp .*d 1d
+} 1
+test regexp-5.5 {exercise cache of compiled expressions} {
+ regexp .*a b
+ regexp .*b c
+ regexp .*c d
+ regexp .*d e
+ regexp .*e f
+ regexp .*e xe
+} 1
+
+test regexp-6.1 {regexp errors} {
+ list [catch {regexp a} msg] $msg
+} {1 {wrong # args: should be "regexp ?switches? exp string ?matchVar? ?subMatchVar subMatchVar ...?"}}
+test regexp-6.2 {regexp errors} {
+ list [catch {regexp -nocase a} msg] $msg
+} {1 {wrong # args: should be "regexp ?switches? exp string ?matchVar? ?subMatchVar subMatchVar ...?"}}
+# XXX
+#test regexp-6.3 {regexp errors} {
+# list [catch {regexp -gorp a} msg] $msg
+#} {1 {bad switch "-gorp": must be -all, -about, -indices, -inline, -expanded, -line, -linestop, -lineanchor, -nocase, -start, or --}}
+test regexp-6.4 {regexp errors} {
+ list [catch {regexp a( b} msg] [string match *parentheses* $msg]
+} {1 1}
+#test regexp-6.5 {regexp errors} {
+# list [catch {regexp a) b} msg] [string match *parentheses* $msg]
+#} {1 1}
+test regexp-6.6 {regexp errors} {
+ 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 regexp-6.7 {regexp errors} {
+ list [catch {regexp (x)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.)(.) xyzzy} msg] $msg
+} {0 0}
+test regexp-6.8 {regexp errors} {
+ catch {unset f1}
+ set f1 44
+ list [catch {regexp abc abc f1(f2)} msg] $msg
+} {1 {can't set "f1(f2)": variable isn't array}}
+test regexp-6.9 {regexp errors, -start bad int check} {
+ list [catch {regexp -start bogus {^$} {}} msg] $msg
+} {1 {bad index "bogus": must be integer?[+-]integer? or end?[+-]integer?}}
+
+test regexp-7.1 {basic regsub operation} {
+ list [regsub aa+ xaxaaaxaa 111&222 foo] $foo
+} {1 xax111aaa222xaa}
+test regexp-7.2 {basic regsub operation} {
+ list [regsub aa+ aaaxaa &111 foo] $foo
+} {1 aaa111xaa}
+test regexp-7.3 {basic regsub operation} {
+ list [regsub aa+ xaxaaa 111& foo] $foo
+} {1 xax111aaa}
+test regexp-7.4 {basic regsub operation} {
+ list [regsub aa+ aaa 11&2&333 foo] $foo
+} {1 11aaa2aaa333}
+test regexp-7.5 {basic regsub operation} {
+ list [regsub aa+ xaxaaaxaa &2&333 foo] $foo
+} {1 xaxaaa2aaa333xaa}
+test regexp-7.6 {basic regsub operation} {
+ list [regsub aa+ xaxaaaxaa 1&22& foo] $foo
+} {1 xax1aaa22aaaxaa}
+test regexp-7.7 {basic regsub operation} {
+ list [regsub a(a+) xaxaaaxaa {1\122\1} foo] $foo
+} {1 xax1aa22aaxaa}
+test regexp-7.8 {basic regsub operation} {
+ list [regsub a(a+) xaxaaaxaa {1\\\122\1} foo] $foo
+} "1 {xax1\\aa22aaxaa}"
+test regexp-7.9 {basic regsub operation} {
+ list [regsub a(a+) xaxaaaxaa {1\\122\1} foo] $foo
+} "1 {xax1\\122aaxaa}"
+test regexp-7.10 {basic regsub operation} {
+ list [regsub a(a+) xaxaaaxaa {1\\&\1} foo] $foo
+} "1 {xax1\\aaaaaxaa}"
+test regexp-7.11 {basic regsub operation} {
+ list [regsub a(a+) xaxaaaxaa {1\&\1} foo] $foo
+} {1 xax1&aaxaa}
+test regexp-7.12 {basic regsub operation} {
+ list [regsub a(a+) xaxaaaxaa {\1\1\1\1&&} foo] $foo
+} {1 xaxaaaaaaaaaaaaaaxaa}
+test regexp-7.13 {basic regsub operation} {
+ set foo xxx
+ list [regsub abc xyz 111 foo] $foo
+} {0 xyz}
+test regexp-7.14 {basic regsub operation} {
+ set foo xxx
+ list [regsub ^ xyz "111 " foo] $foo
+} {1 {111 xyz}}
+test regexp-7.15 {basic regsub operation} {
+ set foo xxx
+ list [regsub -- -foo abc-foodef "111 " foo] $foo
+} {1 {abc111 def}}
+test regexp-7.16 {basic regsub operation} {
+ set foo xxx
+ list [regsub x "" y foo] $foo
+} {0 {}}
+#test regexp-7.17 {regsub utf compliance} {
+# # 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 regexp-8.1 {case conversion in regsub} {
+ list [regsub -nocase a(a+) xaAAaAAay & foo] $foo
+} {1 xaAAaAAay}
+test regexp-8.2 {case conversion in regsub} {
+ list [regsub -nocase a(a+) xaAAaAAay & foo] $foo
+} {1 xaAAaAAay}
+test regexp-8.3 {case conversion in regsub} {
+ set foo 123
+ list [regsub a(a+) xaAAaAAay & foo] $foo
+} {0 xaAAaAAay}
+test regexp-8.4 {case conversion in regsub} {
+ set foo 123
+ list [regsub -nocase a CaDE b foo] $foo
+} {1 CbDE}
+test regexp-8.5 {case conversion in regsub} {
+ set foo 123
+ list [regsub -nocase XYZ CxYzD b foo] $foo
+} {1 CbD}
+test regexp-8.6 {case conversion in regsub} {
+ 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 regexp-9.1 {-all option to regsub} {
+ set foo 86
+ list [regsub -all x+ axxxbxxcxdx |&| foo] $foo
+} {4 a|xxx|b|xx|c|x|d|x|}
+test regexp-9.2 {-all option to regsub} {
+ set foo 86
+ list [regsub -nocase -all x+ aXxXbxxcXdx |&| foo] $foo
+} {4 a|XxX|b|xx|c|X|d|x|}
+test regexp-9.3 {-all option to regsub} {
+ set foo 86
+ list [regsub x+ axxxbxxcxdx |&| foo] $foo
+} {1 a|xxx|bxxcxdx}
+test regexp-9.4 {-all option to regsub} {
+ set foo 86
+ list [regsub -all bc axxxbxxcxdx |&| foo] $foo
+} {0 axxxbxxcxdx}
+test regexp-9.5 {-all option to regsub} {
+ set foo xxx
+ list [regsub -all node "node node more" yy foo] $foo
+} {2 {yy yy more}}
+test regexp-9.6 {-all option to regsub} {
+ set foo xxx
+ list [regsub -all ^ xxx 123 foo] $foo
+} {1 123xxx}
+
+test regexp-10.2 {newline sensitivity in regsub} {
+ set foo xxx
+ list [regsub -line {^a.*b$} "dabc\naxyb\n" 123 foo] $foo
+} "1 {dabc\n123\n}"
+test regexp-10.3 {newline sensitivity in regsub} {
+ set foo xxx
+ list [regsub -line {^a.*b$} "dabc\naxyb\nxb" 123 foo] $foo
+} "1 {dabc\n123\nxb}"
+#test regexp-10.4 {partial newline sensitivity in regsub} {
+# set foo xxx
+# list [regsub -lineanchor {^a.*b$} "da\naxyb\nxb" 123 foo] $foo
+#} "1 {da\n123}"
+#test regexp-10.5 {inverse partial newline sensitivity in regsub} {
+# set foo xxx
+# list [regsub -linestop {a.*b} "da\nbaxyb\nxb" 123 foo] $foo
+#} "1 {da\nb123\nxb}"
+
+test regexp-11.1 {regsub errors} {
+ list [catch {regsub a b} msg] $msg
+} {1 {wrong # args: should be "regsub ?switches? exp string subSpec ?varName?"}}
+test regexp-11.2 {regsub errors} {
+ list [catch {regsub -nocase a b} msg] $msg
+} {1 {wrong # args: should be "regsub ?switches? exp string subSpec ?varName?"}}
+test regexp-11.3 {regsub errors} {
+ list [catch {regsub -nocase -all a b} msg] $msg
+} {1 {wrong # args: should be "regsub ?switches? exp string subSpec ?varName?"}}
+test regexp-11.4 {regsub errors} {
+ list [catch {regsub a b c d e f} msg] $msg
+} {1 {wrong # args: should be "regsub ?switches? exp string subSpec ?varName?"}}
+# XXX
+#test regexp-11.5 {regsub errors} {
+# list [catch {regsub -gorp a b c} msg] $msg
+#} {1 {bad switch "-gorp": must be -all, -nocase, -expanded, -line, -linestop, -lineanchor, -start, or --}}
+test regexp-11.6 {regsub errors} {
+ list [catch {regsub -nocase a( b c d} msg] [string match *parentheses* $msg]
+} {1 1}
+test regexp-11.7 {regsub errors} {
+ catch {unset f1}
+ set f1 44
+ list [catch {regsub -nocase aaa aaa xxx f1(f2)} msg] $msg
+} {1 {can't set "f1(f2)": variable isn't array}}
+test regexp-11.8 {regsub errors, -start bad int check} {
+ list [catch {regsub -start bogus pattern string rep var} msg] $msg
+} {1 {bad index "bogus": must be integer?[+-]integer? or end?[+-]integer?}}
+test regexp-11.9 {regsub without final variable name returns value} {
+ regsub b abaca X
+} {aXaca}
+test regexp-11.10 {regsub without final variable name returns value} {
+ regsub -all a abaca X
+} {XbXcX}
+
+test regexp-11.11 {regsub without final variable name returns value} {
+ regsub b(\[^d\]*)d abcdeabcfde {,&,\1,}
+} {a,bcd,c,eabcfde}
+test regexp-11.12 {regsub without final variable name returns value} {
+ regsub -all b(\[^d\]*)d abcdeabcfde {,&,\1,}
+} {a,bcd,c,ea,bcfd,cf,e}
+
+# 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 regexp-12.1 {Tcl_RegExpExec: large number of subexpressions} {
+ 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 regexp-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 regexp-14.1 {CompileRegexp: regexp cache} {
+ 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 regexp-14.2 {CompileRegexp: regexp cache, different flags} {
+ 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 regexp-15.1 {regexp -start} {
+# catch {unset x}
+# list [regexp -start -10 {\d} 1abc2de3 x] $x
+#} {1 1}
+#test regexp-15.2 {regexp -start} {
+# catch {unset x}
+# list [regexp -start 2 {\d} 1abc2de3 x] $x
+#} {1 2}
+#test regexp-15.3 {regexp -start} {
+# catch {unset x}
+# list [regexp -start 4 {\d} 1abc2de3 x] $x
+#} {1 2}
+#test regexp-15.4 {regexp -start} {
+# catch {unset x}
+# list [regexp -start 5 {\d} 1abc2de3 x] $x
+#} {1 3}
+test regexp-15.5 {regexp -start, over end of string} {
+ catch {unset x}
+ list [regexp -start [string length 1abc2de3] {\d} 1abc2de3 x] [info exists x]
+} {0 0}
+test regexp-15.6 {regexp -start, loss of ^$ behavior} {
+ list [regexp -start 2 {^$} {}]
+} {0}
+test regexp-15.7 {regexp -start, double option} {
+ regexp -start 2 -start 0 a abc
+} 1
+test regexp-15.8 {regexp -start, double option} {
+ regexp -start 0 -start 2 a abc
+} 0
+#test regexp-15.9 {regexp -start, end relative index} {
+# catch {unset x}
+# list [regexp -start end {\d} 1abc2de3 x] [info exists x]
+#} {0 0}
+#test regexp-15.10 {regexp -start, end relative index} {
+# catch {unset x}
+# list [regexp -start end-1 {\d} 1abc2de3 x] [info exists x] $x
+#} {1 1 3}
+#
+#test regexp-16.1 {regsub -start} {
+# catch {unset x}
+# list [regsub -all -start 2 {\d} a1b2c3d4e5 {/&} x] $x
+#} {4 a1b/2c/3d/4e/5}
+test regexp-16.2 {regsub -start} {
+ catch {unset x}
+ list [regsub -all -start -25 {z} hello {/&} x] $x
+} {0 hello}
+test regexp-16.3 {regsub -start} {
+ catch {unset x}
+ list [regsub -all -start 3 {z} hello {/&} x] $x
+} {0 hello}
+#test regexp-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 regexp-16.5 {regsub -start, double option} {
+ list [regsub -start 2 -start 0 a abc c x] $x
+} {1 cbc}
+test regexp-16.6 {regsub -start, double option} {
+ list [regsub -start 0 -start 2 a abc c x] $x
+} {0 abc}
+test regexp-16.7 {regexp -start, end relative index} {
+ list [regsub -start end a aaa b x] $x
+} {0 aaa}
+test regexp-16.8 {regexp -start, end relative index} {
+ list [regsub -start end-1 a aaa b x] $x
+} {1 aab}
+
+test regexp-17.1 {regexp -inline} {
+ regexp -inline b ababa
+} {b}
+test regexp-17.2 {regexp -inline} {
+ regexp -inline (b) ababa
+} {b b}
+test regexp-17.3 {regexp -inline -indices} {
+ regexp -inline -indices (b) ababa
+} {{1 1} {1 1}}
+#test regexp-17.4 {regexp -inline} {
+# regexp -inline {\w(\d+)\w} " hello 23 there456def "
+#} {e456d 456}
+#test regexp-17.5 {regexp -inline no matches} {
+# regexp -inline {\w(\d+)\w} ""
+#} {}
+test regexp-17.6 {regexp -inline no matches} {
+ regexp -inline hello goodbye
+} {}
+test regexp-17.7 {regexp -inline, no matchvars allowed} {
+ list [catch {regexp -inline b abc match} msg] $msg
+} {1 {regexp match variables not allowed when using -inline}}
+
+test regexp-18.1 {regexp -all} {
+ regexp -all b bbbbb
+} {5}
+test regexp-18.2 {regexp -all} {
+ regexp -all b abababbabaaaaaaaaaab
+} {6}
+test regexp-18.3 {regexp -all -inline} {
+ regexp -all -inline b abababbabaaaaaaaaaab
+} {b b b b b b}
+#test regexp-18.4 {regexp -all -inline} {
+# regexp -all -inline {\w(\w)} abcdefg
+#} {ab b cd d ef f}
+#test regexp-18.5 {regexp -all -inline} {
+# regexp -all -inline {\w(\w)$} abcdefg
+#} {fg g}
+#test regexp-18.6 {regexp -all -inline} {
+# regexp -all -inline {\d+} 10:20:30:40
+#} {10 20 30 40}
+test regexp-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 regexp-18.8 {regexp -all} {
+ # This should not cause an infinite loop
+ regexp -all -inline {a*} a
+} {a}
+test regexp-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 regexp-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 regexp-18.11 {regexp -all} {
+ regexp -all -inline {^a} aaaa
+} {a}
+test regexp-18.12 {regexp -all -inline -indices} {
+ 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 regexp-19.1 {regsub null replacement} {
+ regsub -all {@} {@hel@lo@} "\0a\0" result
+ list $result [string length $result]
+} "\0a\0hel\0a\0lo\0a\0 14"
+
+#test regexp-20.1 {regsub shared object shimmering} {
+# # Bug #461322
+# set a abcdefghijklmnopqurstuvwxyz
+# set b $a
+# set c abcdefghijklmnopqurstuvwxyz0123456789
+# regsub $a $c $b d
+# list $d [string length $d] [string bytelength $d]
+#} [list abcdefghijklmnopqurstuvwxyz0123456789 37 37]
+#test regexp-20.2 {regsub shared object shimmering with -about} {
+# eval regexp -about abc
+#} {0 {}}
+
+test regexp-21.1 {regsub works with empty string} {
+ regsub -- ^ {} foo
+} {foo}
+
+test regexp-21.2 {regsub works with empty string} {
+ regsub -- \$ {} foo
+} {foo}
+
+test regexp-21.3 {regsub works with empty string offset} {
+ regsub -start 0 -- ^ {} foo
+} {foo}
+
+test regexp-21.4 {regsub works with empty string offset} {
+ regsub -start 0 -- \$ {} foo
+} {foo}
+
+test regexp-21.5 {regsub works with empty string offset} {
+ regsub -start 3 -- \$ {123} foo
+} {123foo}
+
+test regexp-21.6 {regexp works with empty string} {
+ regexp -- ^ {}
+} {1}
+
+test regexp-21.7 {regexp works with empty string} {
+ regexp -start 0 -- ^ {}
+} {1}
+
+test regexp-21.8 {regexp works with empty string offset} {
+ regexp -start 3 -- ^ {123}
+} {0}
+
+test regexp-21.9 {regexp works with empty string offset} {
+ regexp -start 3 -- \$ {123}
+} {1}
+
+#test regexp-21.10 {multiple matches handle newlines} {
+# regsub -all -lineanchor -- {^#[^\n]*\n} "#one\n#two\n#three\n" foo\n
+#} "foo\nfoo\nfoo\n"
+
+test regexp-21.11 {multiple matches handle newlines} {
+ regsub -all -line -- ^ "a\nb\nc" \#
+} "\#a\n\#b\n\#c"
+
+test regexp-21.12 {multiple matches handle newlines} {
+ regsub -all -line -- ^ "\n\n" \#
+} "\#\n\#\n\#"
+
+test regexp-21.13 {multiple matches handle newlines} {
+ regexp -all -inline -indices -line -- ^ "a\nb\nc"
+} {{0 -1} {2 1} {4 3}}
+
+test regexp-22.1 {effect of caching} {
set filedata {BEGIN_TABLE ;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;; END_TABLE}
@@ -33,9 +673,4 @@ test regexp-1.1 {effect of caching} {
expr {$t2 * 1.0 / $t1 < 1.2 && $t1 * 1.0 / $t2 < 1.2}
} {0}
-test regexp-1.2 {Non-ascii} {
- set nbsp [format %c 0xa0]
- set string [format "abc%cdef" 0xa0]
-
- list [regexp "(.*)[set nbsp](.*)" $string dummy f1 f2] $f1 $f2
-} {1 abc def}
+testreport