From ba387764ca1590625d349e74eb8a8a64d1849b67 Mon Sep 17 00:00:00 2001 From: Tulir Asokan Date: Wed, 14 Nov 2018 00:00:35 +0200 Subject: Fix things --- vendor/gopkg.in/russross/blackfriday.v2/inline.go | 18 ++++++++++++++++-- 1 file changed, 16 insertions(+), 2 deletions(-) (limited to 'vendor/gopkg.in/russross/blackfriday.v2/inline.go') diff --git a/vendor/gopkg.in/russross/blackfriday.v2/inline.go b/vendor/gopkg.in/russross/blackfriday.v2/inline.go index 3d63310..4ed2907 100644 --- a/vendor/gopkg.in/russross/blackfriday.v2/inline.go +++ b/vendor/gopkg.in/russross/blackfriday.v2/inline.go @@ -23,8 +23,22 @@ var ( urlRe = `((https?|ftp):\/\/|\/)[-A-Za-z0-9+&@#\/%?=~_|!:,.;\(\)]+` anchorRe = regexp.MustCompile(`^(]+")?\s?>` + urlRe + `<\/a>)`) - // TODO: improve this regexp to catch all possible entities: - htmlEntityRe = regexp.MustCompile(`&[a-z]{2,5};`) + // https://www.w3.org/TR/html5/syntax.html#character-references + // highest unicode code point in 17 planes (2^20): 1,114,112d = + // 7 dec digits or 6 hex digits + // named entity references can be 2-31 characters with stuff like < + // at one end and ∳ at the other. There + // are also sometimes numbers at the end, although this isn't inherent + // in the specification; there are never numbers anywhere else in + // current character references, though; see ¾ and ▒, etc. + // https://www.w3.org/TR/html5/syntax.html#named-character-references + // + // entity := "&" (named group | number ref) ";" + // named group := [a-zA-Z]{2,31}[0-9]{0,2} + // number ref := "#" (dec ref | hex ref) + // dec ref := [0-9]{1,7} + // hex ref := ("x" | "X") [0-9a-fA-F]{1,6} + htmlEntityRe = regexp.MustCompile(`&([a-zA-Z]{2,31}[0-9]{0,2}|#([0-9]{1,7}|[xX][0-9a-fA-F]{1,6}));`) ) // Functions to parse text within a block -- cgit v1.2.3