![[첫화면으로]](/raymundo_logo.jpg){kind=logo}
UTF-8이전작업/링크패턴UTF-8이전작업/링크패턴
/* 위키 페이지 링크 */ A.wikipagelink:link, A.wikipagelink:active, A.wikipagelink:visited, A.wikipagelink:hover { background: transparent; color: green; text-decoration: none; } A.wikipagelink:hover { text-decoration: underline; } /* 위키 페이지 편집 링크 */ A.wikipageedit:link, A.wikipageedit:active, A.wikipageedit:visited, A.wikipageedit:hover { background: transparent; color: red; text-decoration: none; } A.wikipageedit:hover { text-decoration: underline; }
그 외의 패턴은 InitLinkPatterns 함수의 diff로 설명을 대신함: 사실 패턴의 의미 자체가 달라진 건 거의 없고, oddmuse를 따라서 문자의 코드값 범위를 \x80-\xff 로 넓힌 게 핵심.
sub InitLinkPatterns {
my ($UpperLetter, $LowerLetter, $AnyLetter, $LpA, $LpB, $QDelim);
# Field separators are used in the URL-style patterns below.
# $FS = "\xb3"; # The FS character is a superscript "3"
- $FS = "\x7f";
+ $FS = "\x1e"; # by gypark. from oddmuse
$FS1 = $FS . "1"; # The FS values are used to separate fields
$FS2 = $FS . "2"; # in stored hashtables and other data structures.
$FS3 = $FS . "3"; # The FS character is not allowed in user data.
###############
### added by gypark
$FS_lt = $FS . "lt";
$FS_gt = $FS . "gt";
###
###############
-
- $UpperLetter = "[A-Z";
- $LowerLetter = "[a-z";
- $AnyLetter = "[A-Za-z";
- if ($NonEnglish) {
- $UpperLetter .= "\xc0-\xde";
- $LowerLetter .= "\xdf-\xff";
- $AnyLetter .= "\xc0-\xff";
- }
- if (!$SimpleLinks) {
- $AnyLetter .= "_0-9";
- }
- $UpperLetter .= "]"; $LowerLetter .= "]"; $AnyLetter .= "]";
+ $UpperLetter = "[A-Z\xc0-\xde]";
+ $LowerLetter = "[a-z\xdf-\xff]";
+ $AnyLetter = "[A-Za-z\x80-\xff_0-9]";
# Main link pattern: lowercase between uppercase, then anything
$LpA = $UpperLetter . "+" . $LowerLetter . "+" . $UpperLetter
. $AnyLetter . "*";
# Optional subpage link pattern: uppercase, lowercase, then anything
$LpB = $UpperLetter . "+" . $LowerLetter . "+" . $AnyLetter . "*";
if ($UseSubpage) {
# Loose pattern: If subpage is used, subpage may be simple name
$LinkPattern = "((?:(?:$LpA)?\\/$LpB)|$LpA)";
# Strict pattern: both sides must be the main LinkPattern
# $LinkPattern = "((?:(?:$LpA)?\\/)?$LpA)";
} else {
$LinkPattern = "($LpA)";
}
$QDelim = '(?:"")?'; # Optional quote delimiter (not in output)
-###############
-### replaced by gypark
-### anchor 에 한글 사용
-# $AnchoredLinkPattern = $LinkPattern . '#(\\w+)' . $QDelim if $NamedAnchors;
- $AnchoredLinkPattern = $LinkPattern . '#([0-9A-Za-z\xa0-\xff]+)' . $QDelim if $NamedAnchors;
-###
-###############
$LinkPattern .= $QDelim;
# Inter-site convention: sites must start with uppercase letter
# (Uppercase letter avoids confusion with URLs)
$InterSitePattern = $UpperLetter . $AnyLetter . "+";
$InterLinkPattern = "((?:$InterSitePattern:[^\\]\\s\"<>$FS]+)$QDelim)";
+ # free link [[pagename]]
if ($FreeLinks) {
# Note: the - character must be first in $AnyLetter definition
- #if ($NonEnglish) {
- $AnyLetter = "[-,.()' _0-9A-Za-z\xa0-\xff]";
- #} else {
- # $AnyLetter = "[-,.()' _0-9A-Za-z]";
- #}
+ $AnyLetter = "[-,.()' _0-9A-Za-z\x80-\xff]";
}
- $FreeLinkPattern = "($AnyLetter+)";
if ($UseSubpage) {
$FreeLinkPattern = "((?:(?:$AnyLetter+)?\\/)?$AnyLetter+)";
+ } else {
+ $FreeLinkPattern = "($AnyLetter+)";
}
$FreeLinkPattern .= $QDelim;
-###############
-### added by gypark
-### 한글패이지에 anchor 사용
-### from Bab2's patch
- $AnchoredFreeLinkPattern = $FreeLinkPattern . '#([0-9A-Za-z\xa0-\xff]+)' . $QDelim if $NamedAnchors;
-###
-###############
+ # anchored link
+ $AnchorPattern = '#([0-9A-Za-z\x80-\xff]+)';
+ $AnchoredLinkPattern = $LinkPattern . $AnchorPattern . $QDelim if $NamedAnchors;
+ $AnchoredFreeLinkPattern = $FreeLinkPattern . $AnchorPattern . $QDelim if $NamedAnchors;
# Url-style links are delimited by one of:
# 1. Whitespace (kept in output)
# 2. Left or right angle-bracket (< or >) (kept in output)
# 3. Right square-bracket (]) (kept in output)
# 4. A single double-quote (") (kept in output)
# 5. A $FS (field separator) character (kept in output)
# 6. A double double-quote ("") (removed from output)
-
- $UrlProtocols = "http|https|ftp|afs|news|nntp|mid|cid|mailto|wais|mms|mmst|"
- . "prospero|telnet|gopher";
- $UrlProtocols .= '|file' if $NetworkFile;
+ $UrlProtocols = 'http|https|ftp|afs|news|nntp|mid|cid|mailto|wais|mms|mmst|prospero|telnet|gopher|irc';
+ $UrlProtocols .= '|file' if $NetworkFile;
$UrlPattern = "((?:(?:$UrlProtocols):[^\\]\\s\"<>$FS]+)$QDelim)";
$ImageExtensions = "(gif|jpg|png|bmp|jpeg|GIF|JPG|PNG|BMP|JPEG)";
$RFCPattern = "RFC\\s?(\\d+)";
-###############
-### replaced by gypark
-### ISBN 패턴 수정
-# $ISBNPattern = "ISBN:?([0-9- xX]{10,})";
$ISBNPattern = "ISBN:?([0-9-xX]{10,})";
-###
-###############
}
sub InitLinkPatterns { my ($UpperLetter, $LowerLetter, $AnyLetter, $WikiWord, $QDelim); $QDelim = '(?:"")?';# Optional quote delimiter (removed from the output) $WikiWord = '[A-Z]+[a-z\x80-\xff]+[A-Z][A-Za-z\x80-\xff]*'; $LinkPattern = "($WikiWord)$QDelim"; $FreeLinkPattern = "([-,.()' _0-9A-Za-z\x80-\xff]+)"; # Intersites must start with uppercase letter to avoid confusion with URLs. $InterSitePattern = '[A-Z\x80-\xff]+[A-Za-z\x80-\xff]+'; $InterLinkPattern = "($InterSitePattern:[-a-zA-Z0-9\x80-\xff_=!?#\$\@~`\%&*+\\/:;.,]*[-a-zA-Z0-9\x80-\xff_=#\$\@~`\%&*+\\/])$QDelim"; $FreeInterLinkPattern = "($InterSitePattern:[-a-zA-Z0-9\x80-\xff_=!?#\$\@~`\%&*+\\/:;.,()' ]+)"; # plus space and other characters, and no restrictions on the end of the pattern $UrlProtocols = 'http|https|ftp|afs|news|nntp|mid|cid|mailto|wais|prospero|telnet|gopher|irc'; $UrlProtocols .= '|file' if $NetworkFile; my $UrlChars = '[-a-zA-Z0-9/@=+$_~*.,;:?!\'"()&#%]'; # see RFC 2396 my $EndChars = '[-a-zA-Z0-9/@=+$_~*]'; # no punctuation at the end of the url. $UrlPattern = "((?:$UrlProtocols):$UrlChars+$EndChars)"; $FullUrlPattern="((?:$UrlProtocols):$UrlChars+)"; # when used in square brackets $ImageExtensions = '(gif|jpg|png|bmp|jpeg)'; }
소스 보다가 잘 모르겠어서... $QDelim은 뭐하는 걸까요?
조프위키를 보면" 여기서 '키'와 '를' 사이에 넣었습니다.