AuroraMiddleware/scuffed-code
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

ICU-2422 regexp tests, work in progress.

Browse Source 
X-SVN-Rev: 10961
This commit is contained in:
Andy Heninger 2003-02-05 06:50:32 +00:00
parent 933bece24a
commit 6415f52007
3 changed files with 63 additions and 60 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
icu4c/source/i18n/rematch.cpp
View File

@ -271,7 +271,7 @@ UBool RegexMatcher::find() {
int32_t startPos = fMatchEnd;
int32_t inputLen = fInput->length();
U_ASSERT(startPos >= 0 && startPos <= inputLen);
U_ASSERT(startPos >= 0);
for (;;) {
MatchAt(startPos, status);
if (U_FAILURE(status)) {

17
icu4c/source/test/intltest/regextst.cpp
View File

@ -57,7 +57,7 @@ void RegexTest::runIndexedTest( int32_t index, UBool exec, const char* &name, ch
if (exec) API_Pattern();
break;
case 4: name = "Extended";
//if (exec) Extended();
if (exec) Extended();
break;
case 5: name = "Errors";
if (exec) Errors();
@ -1092,11 +1092,12 @@ void RegexTest::Extended() {
RegexMatcher quotedStuffMat("\\s*?([\\'\\\"/])(.+?)\\1", 0, status);
RegexMatcher commentMat ("\\s*?(#.*)?$", 0, status);
RegexMatcher flagsMat ("\\s*?([ixsmdt]*)(a?)", 0, status);
RegexMatcher flagsMat ("\\s*?([ixsmdt]*)([:letter:]*)", 0, status);
RegexMatcher lineMat("(.+?)[\\r\\n]+", testString, 0, status);
RegexMatcher lineMat("(.*?)\\r?\\n", testString, 0, status);
UnicodeString testPattern; // The pattern for test from the test file.
UnicodeString testFlags; // the flags for a test.
UnicodeString matchString; // The marked up string to be used as input
@ -1105,8 +1106,15 @@ void RegexTest::Extended() {
//
while (lineMat.find()) {
lineNum++;
if (U_FAILURE(status)) {
errln("line %d: ICU Error \"%s\"", lineNum, u_errorName(status));
}
status = U_ZERO_ERROR;
UnicodeString testLine = lineMat.group(1, status);
if (testLine.length() == 0) {
continue;
}
//
// Parse the test line. Skip blank and comment only lines.
@ -1151,13 +1159,12 @@ void RegexTest::Extended() {
//
quotedStuffMat.reset(testLine);
if (quotedStuffMat.lookingAt(status)) {
testString = quotedStuffMat.group(2, status);
matchString = quotedStuffMat.group(2, status);
testLine.remove(0, quotedStuffMat.end(0, status));
} else {
errln("Bad match string at test file line %d", lineNum);
continue;
}
testLine.remove(0, quotedStuffMat.end(0, status));
//
// The only thing left from the input line should be an optional trailing comment.

104
icu4c/source/test/testdata/regextst.txt vendored
View File

@ -1,5 +1,5 @@
#
# file: regextst.txt
# file:
#
# ICU regular expression test cases.
#
@ -22,7 +22,7 @@
# Capturing parens
".(..)." "<0>a<1>bc</1>d</0>"
".*\\A( +hello)" "<0><1> hello</1></0>"
".*\A( +hello)" "<0><1> hello</1></0>"
"(hello)|(goodbye)" "<0><1>hello</1></0>"
"(hello)|(goodbye)" "<0><2>goodbye</2></0>"
"abc( +( inner(X?) +) xyz)" "leading cruft <0>abc<1> <2> inner<3></3> </2> xyz</1></0> cruft"
@ -48,54 +48,50 @@
"(ab)(ab)\?\?(ab)\?\?(ab)\?\?(ab)\?\?c" "<0><1>ab</1><4>ab</4><5>ab</5>c</0>"
# Unicode Properties as naked elements in a pattern
"\\p{Lu}+" "here we go ... <0>ABC</0> and no more."
"(\\p{L}+)(\\P{L}*?) (\\p{Zs}*)" "7999<0><1>letters</1><2>4949%^&*(</2> <3> </3></0>"
"\p{Lu}+" "here we go ... <0>ABC</0> and no more."
"(\p{L}+)(\P{L}*?) (\p{Zs}*)" "7999<0><1>letters</1><2>4949%^&*(</2> <3> </3></0>"
# \w and \W
"\\w+" " $%^&*( <0>hello123</0>%^&*("
"\\W+" "<0> $%^&*( </0>hello123%^&*("
"\w+" " $%^&*( <0>hello123</0>%^&*("
"\W+" "<0> $%^&*( </0>hello123%^&*("
# \A match at beginning of input only.
".*\\Ahello" "<0>hello</0> hello"
".*\Ahello" "<0>hello</0> hello"
".*hello" "<0>hello hello</0>"
".*\\Ahello" "stuff\nhello"# don't match after embedded new-line.
".*\Ahello" "stuff\nhello" # don't match after embedded new-line.
# \b \B
".*?\\b(.).*" "<0> $%^&*( <1>h</1>ello123%^&*()gxx</0>"
"\\ba\\b" "-<0>a</0>"
"\\by\\b" "xy"
".*?\b(.).*" "<0> $%^&*( <1>h</1>ello123%^&*()gxx</0>"
"\ba\b" "-<0>a</0>"
"\by\b" "xy"
# Finds first chars of up to 5 words
"(?:.*?\\b(\\w))?(?:.*?\\b(\\w))?(?:.*?\\b(\\w))?(?:.*?\\b(\\w))?(?:.*?\\b(\\w))?" "<0><1>T</1>the <2>q</2>ick <3>b</3>rown <4>f</4></0>ox"
"H.*?((?:\\B.)+)" "<0>H<1>ello</1></0> "
".*?((?:\\B.)+).*?((?:\\B.)+).*?((?:\\B.)+)",
"<0>H<1>ello</1> <2> </2>g<3>oodbye</3></0> "
"(?:.*?\b(\w))?(?:.*?\b(\w))?(?:.*?\b(\w))?(?:.*?\b(\w))?(?:.*?\b(\w))?" "<0><1>T</1>the <2>q</2>ick <3>b</3>rown <4>f</4></0>ox"
"H.*?((?:\B.)+)" "<0>H<1>ello</1></0> "
".*?((?:\B.)+).*?((?:\B.)+).*?((?:\B.)+)" "<0>H<1>ello</1> <2> </2>g<3>oodbye</3></0> "
"(?:.*?\\b(.))?(?:.*?\\b(.))?(?:.*?\\b(.))?(?:.*?\\b(.))?(?:.*?\\b(.))?.*" "<0> \\u0301 \\u0301<1>A</1>\\u0302BC\\u0303\\u0304<2> </2>\\u0305 \\u0306<3>X</3>\\u0307Y\\u0308</0>"
"(?:.*?\b(.))?(?:.*?\b(.))?(?:.*?\b(.))?(?:.*?\b(.))?(?:.*?\b(.))?.*" "<0> \u0301 \u0301<1>A</1>\u0302BC\u0303\u0304<2> </2>\u0305 \u0306<3>X</3>\u0307Y\u0308</0>"
# . does not match new-lines
"." "\\u000a\\u000d\\u0085\\u000c\\u2028\\u2029<0>X</0>\\u000aY"
"A." "A\\u000a "# no match
"." "\u000a\u000d\u0085\u000c\u2028\u2029<0>X</0>\u000aY"
"A." "A\u000a "# no match
# \d for decimal digits
"\\d*" "<0>0123456789\\u0660\\u06F9\\u0969\\u0A66\\u1369"
"\\u17E2\\uFF10\\U0001D7CE\\U0001D7FF</0>non-digits"
"\\D+" "<0>non digits</0>"
"\\D*(\\d*)(\\D*)" "<0>non-digits<1>3456666</1><2>more non digits</2></0>"
"\d*" "<0>0123456789\u0660\u06F9\u0969\u0A66\u1369\u17E2\uFF10\U0001D7CE\U0001D7FF</0>non-digits"
"\D+" "<0>non digits</0>"
"\D*(\d*)(\D*)" "<0>non-digits<1>3456666</1><2>more non digits</2></0>"
# \Q...\E quote mode
"hel\\Qlo, worl\\Ed" "<0>hello, world</0>"
"\\Q$*^^(*)?\\A\\E(a*)" "<0>$*^^(*)?\\\\A<1>aaaaaaaaaaaaaaa</1></0>"
"hel\Qlo, worl\Ed" "<0>hello, world</0>"
"\Q$*^^(*)?\A\E(a*)" "<0>$*^^(*)?\A<1>aaaaaaaaaaaaaaa</1></0>"
# \S and \s space characters
"\\s+" "not_space<0> \\t \\r \\n \\u3000 \\u2004 \\u2028 \\u2029</0>xyz"
"(\\S+).*?(\\S+).*" "<0><1>Not-spaces</1> <2>more-non-spaces</2> </0>"
"\s+" "not_space<0> \t \r \n \u3000 \u2004 \u2028 \u2029</0>xyz"
"(\S+).*?(\S+).*" "<0><1>Not-spaces</1> <2>more-non-spaces</2> </0>"
# \X consume one combining char sequence.
"(\\X)?(\\X)?(\\X)?(\\X)?(\\X)?(\\X)?(\\X)?(\\X)?(\\X)?(\\X)?(\\X)?(\\X)?",
"<0><1>A</1><2>B</2><3> </3><4>\\r\\n</4></0>"
"(\\X)?(\\X)?(\\X)?(\\X)?(\\X)?(\\X)?(\\X)?(\\X)?(\\X)?(\\X)?(\\X)?(\\X)?",
"<0><1>A\\u0301</1><2>\n</2><3>\\u0305</3><4>a\\u0302\\u0303\\u0304</4></0>"
"(\X)?(\X)?(\X)?(\X)?(\X)?(\X)?(\X)?(\X)?(\X)?(\X)?(\X)?(\X)?" "<0><1>A</1><2>B</2><3> </3><4>\r\n</4></0>"
"(\X)?(\X)?(\X)?(\X)?(\X)?(\X)?(\X)?(\X)?(\X)?(\X)?(\X)?(\X)?" "<0><1>A\u0301</1><2>\n</2><3>\u0305</3><4>a\u0302\u0303\u0304</4></0>"
# ^ matches only at beginning of line
".*^(Hello)" "<0><1>Hello</1></0> Hello Hello Hello Goodbye"
@ -107,31 +103,31 @@
".*?(Goodbye)" "<0>Hello <1>Goodbye</1></0> Goodbye Goodbye"
".*?(Goodbye)$" "Hello Goodbye> Goodbye Goodbye "# No Match
".*?(Goodbye)$" "<0>Hello Goodbye Goodbye <1>Goodbye</1></0>\\n"
".*?(Goodbye)$" "<0>Hello Goodbye Goodbye <1>Goodbye</1></0>\\n"
".*?(Goodbye)$" "<0>Hello Goodbye Goodbye <1>Goodbye</1></0>\\r\\n"
".*?(Goodbye)$" "Hello Goodbye Goodbye Goodbye\\n\\n"# No Match
".*?(Goodbye)$" "<0>Hello Goodbye Goodbye <1>Goodbye</1></0>\n"
".*?(Goodbye)$" "<0>Hello Goodbye Goodbye <1>Goodbye</1></0>\n"
".*?(Goodbye)$" "<0>Hello Goodbye Goodbye <1>Goodbye</1></0>\r\n"
".*?(Goodbye)$" "Hello Goodbye Goodbye Goodbye\n\n"# No Match
# \Z matches at end of input, like $ with default flags.
".*?(Goodbye)\\Z" "<0>Hello Goodbye Goodbye <1>Goodbye</1></0>"
".*?(Goodbye)\Z" "<0>Hello Goodbye Goodbye <1>Goodbye</1></0>"
".*?(Goodbye)" "<0>Hello <1>Goodbye</1></0> Goodbye Goodbye"
".*?(Goodbye)\\Z" "Hello Goodbye> Goodbye Goodbye "# No Match
"here$" "here\\nthe end"# No Match
".*?(Goodbye)\Z" "Hello Goodbye> Goodbye Goodbye "# No Match
"here$" "here\nthe end"# No Match
".*?(Goodbye)\\Z" "<0>Hello Goodbye Goodbye <1>Goodbye</1></0>\\n"
".*?(Goodbye)\\Z" "<0>Hello Goodbye Goodbye <1>Goodbye</1></0>\\n"
".*?(Goodbye)\\Z" "<0>Hello Goodbye Goodbye <1>Goodbye</1></0>\\r\\n"
".*?(Goodbye)\\Z" "Hello Goodbye Goodbye Goodbye\\n\\n"# No Match
".*?(Goodbye)\Z" "<0>Hello Goodbye Goodbye <1>Goodbye</1></0>\n"
".*?(Goodbye)\Z" "<0>Hello Goodbye Goodbye <1>Goodbye</1></0>\n"
".*?(Goodbye)\Z" "<0>Hello Goodbye Goodbye <1>Goodbye</1></0>\r\n"
".*?(Goodbye)\Z" "Hello Goodbye Goodbye Goodbye\n\n"# No Match
# \z matches only at the end of string.
# no special treatment of new lines.
# no dependencies on flag settings.
".*?(Goodbye)\\z" "<0>Hello Goodbye Goodbye <1>Goodbye</1></0>"
".*?(Goodbye)\\z" "Hello Goodbye Goodbye Goodbye "# No Match
"here$" "here\\nthe end"# No Match
".*?(Goodbye)\z" "<0>Hello Goodbye Goodbye <1>Goodbye</1></0>"
".*?(Goodbye)\z" "Hello Goodbye Goodbye Goodbye "# No Match
"here$" "here\nthe end"# No Match
".*?(Goodbye)\\z" "Hello Goodbye Goodbye Goodbye\\n"# No Match
".*?(Goodbye)\\n\\z" "<0>Hello Goodbye Goodbye <1>Goodbye</1>\\n</0>"
".*?(Goodbye)\z" "Hello Goodbye Goodbye Goodbye\n"# No Match
".*?(Goodbye)\n\z" "<0>Hello Goodbye Goodbye <1>Goodbye</1>\n</0>"
# (?# comment) doesn't muck up pattern
"Hello (?# this is a comment) world" " <0>Hello world</0>..."
@ -145,7 +141,7 @@
"ABC+" "<0>ABCCCC</0>ABC"
"(?:ABC)+" "<0>ABCABCABC</0>D"
"(?:ABC)DEF+" "<0>ABCDEFFF</0>D"
"AB\\.C\\eD\\u0666E" "<0>AB.C\\u001BD\\u0666E</0>F"
"AB\.C\eD\u0666E" "<0>AB.C\u001BD\u0666E</0>F"
# {min,max} iteration qualifier
@ -188,8 +184,8 @@
# Atomic Grouping
"(?>.*)abc" "abcabcabc" # no match. .* consumed entire string.
"(?>(abc{2,4}?))(c*)" "<0><1>abcc</1><2>ccc</2></0>ddd"
"(\\.\\d\\d(?>[1-9]?))\\d+" "1.625"
"(\\.\\d\\d(?>[1-9]?))\\d+" "1<0><1>.625</1>0</0>"
"(\.\d\d(?>[1-9]?))\d+" "1.625"
"(\.\d\d(?>[1-9]?))\d+" "1<0><1>.625</1>0</0>"
# Possessive *+
"(abc)*+a" "abcabcabc"
@ -202,8 +198,8 @@
"c?cddd" "<0>cddd</0>"
# Back Reference
"(?:ab(..)cd\\1)*" "<0>ab23cd23ab<1>ww</1>cdww</0>abxxcdyy"
"ab(?:c|(d?))(\\1)" "<0>ab<1><2></2></1></0>c"
"ab(?:c|(d?))(\\1)" "<0>ab<1>d</1><2>d</2></0>"
"ab(?:c|(d?))(\\1)" "<0>ab<1></1><2></2></0>e"
"ab(?:c|(d?))(\\1)" "<0>ab<1></1><2></2></0>"
"(?:ab(..)cd\1)*" "<0>ab23cd23ab<1>ww</1>cdww</0>abxxcdyy"
"ab(?:c|(d?))(\1)" "<0>ab<1><2></2></1></0>c"
"ab(?:c|(d?))(\1)" "<0>ab<1>d</1><2>d</2></0>"
"ab(?:c|(d?))(\1)" "<0>ab<1></1><2></2></0>e"
"ab(?:c|(d?))(\1)" "<0>ab<1></1><2></2></0>"