diff options
Diffstat (limited to 'Master/texmf-dist/context/data/scite/lexers/scite-context-lexer-xml.lua')
| -rw-r--r-- | Master/texmf-dist/context/data/scite/lexers/scite-context-lexer-xml.lua | 213 |
1 files changed, 111 insertions, 102 deletions
diff --git a/Master/texmf-dist/context/data/scite/lexers/scite-context-lexer-xml.lua b/Master/texmf-dist/context/data/scite/lexers/scite-context-lexer-xml.lua index 241e2259123..77c89b1d677 100644 --- a/Master/texmf-dist/context/data/scite/lexers/scite-context-lexer-xml.lua +++ b/Master/texmf-dist/context/data/scite/lexers/scite-context-lexer-xml.lua @@ -12,26 +12,28 @@ local info = { -- todo: parse entities in attributes -if not lexer._CONTEXTEXTENSIONS then require("scite-context-lexer") end - -local lexer = lexer local global, string, table, lpeg = _G, string, table, lpeg -local token, exact_match = lexer.token, lexer.exact_match -local P, R, S, V, C, Cmt, Ct, Cp = lpeg.P, lpeg.R, lpeg.S, lpeg.V, lpeg.C, lpeg.Cmt, lpeg.Ct, lpeg.Cp +local P, R, S, C, Cmt, Cp = lpeg.P, lpeg.R, lpeg.S, lpeg.C, lpeg.Cmt, lpeg.Cp local type = type local match, find = string.match, string.find -local xmllexer = { _NAME = "xml", _FILENAME = "scite-context-lexer-xml" } -local whitespace = lexer.WHITESPACE -- triggers states +local lexer = require("lexer") local context = lexer.context +local patterns = context.patterns + +local token = lexer.token +local exact_match = lexer.exact_match -local xmlcommentlexer = lexer.load("scite-context-lexer-xml-comment") -- indirect (some issue with the lexer framework) -local xmlcdatalexer = lexer.load("scite-context-lexer-xml-cdata") -- indirect (some issue with the lexer framework) -local xmlscriptlexer = lexer.load("scite-context-lexer-xml-script") -- indirect (some issue with the lexer framework) -local lualexer = lexer.load("scite-context-lexer-lua") -- +local xmllexer = lexer.new("xml","scite-context-lexer-xml") +local whitespace = xmllexer.whitespace -local space = lexer.space -- S(" \t\n\r\v\f") -local any = lexer.any -- P(1) +local xmlcommentlexer = lexer.load("scite-context-lexer-xml-comment") +local xmlcdatalexer = lexer.load("scite-context-lexer-xml-cdata") +local xmlscriptlexer = lexer.load("scite-context-lexer-xml-script") +local lualexer = lexer.load("scite-context-lexer-lua") + +local space = patterns.space +local any = patterns.any local dquote = P('"') local squote = P("'") @@ -40,7 +42,7 @@ local semicolon = P(";") local equal = P("=") local ampersand = P("&") -local name = (R("az","AZ","09") + S('_-.'))^1 +local name = (R("az","AZ","09") + S("_-."))^1 local openbegin = P("<") local openend = P("</") local closebegin = P("/>") + P(">") @@ -84,12 +86,12 @@ local validminimum = 3 -- -- <?context-directive editor language us ?> -local p_preamble = Cmt(#P("<?xml "), function(input,i,_) -- todo: utf bomb +local t_preamble = Cmt(P("<?xml "), function(input,i,_) -- todo: utf bomb, no longer # if i < 200 then validwords, validminimum = false, 3 local language = match(input,"^<%?xml[^>]*%?>%s*<%?context%-directive%s+editor%s+language%s+(..)%s+%?>") -- if not language then - -- language = match(input,'^<%?xml[^>]*language=[\"\'](..)[\"\'][^>]*%?>',i) + -- language = match(input,"^<%?xml[^>]*language=[\"\'](..)[\"\'][^>]*%?>",i) -- end if language then validwords, validminimum = setwordlist(language) @@ -98,24 +100,23 @@ local p_preamble = Cmt(#P("<?xml "), function(input,i,_) -- todo: utf bomb return false end) -local p_word = +local t_word = -- Ct( iwordpattern / function(s) return styleofword(validwords,validminimum,s) end * Cp() ) -- the function can be inlined iwordpattern / function(s) return styleofword(validwords,validminimum,s) end * Cp() -- the function can be inlined -local p_rest = +local t_rest = token("default", any) -local p_text = +local t_text = token("default", (1-S("<>&")-space)^1) -local p_spacing = +local t_spacing = token(whitespace, space^1) --- token("whitespace", space^1) -local p_optionalwhitespace = - p_spacing^0 +local t_optionalwhitespace = + token("default", space^1)^0 -local p_localspacing = +local t_localspacing = token("default", space^1) -- Because we want a differently colored open and close we need an embedded lexer (whitespace @@ -123,22 +124,22 @@ local p_localspacing = -- Even using different style keys is not robust as they can be shared. I'll fix the main -- lexer code. -local p_sstring = +local t_sstring = token("quote",dquote) * token("string",(1-dquote)^0) -- different from context * token("quote",dquote) -local p_dstring = +local t_dstring = token("quote",squote) * token("string",(1-squote)^0) -- different from context * token("quote",squote) --- local p_comment = +-- local t_comment = -- token("command",opencomment) -- * token("comment",(1-closecomment)^0) -- different from context -- * token("command",closecomment) --- local p_cdata = +-- local t_cdata = -- token("command",opencdata) -- * token("comment",(1-closecdata)^0) -- different from context -- * token("command",closecdata) @@ -156,74 +157,74 @@ local p_dstring = -- <!ENTITY xxxx PUBLIC "yyyy" > -- <!ENTITY xxxx "yyyy" > -local p_docstr = p_dstring + p_sstring +local t_docstr = t_dstring + t_sstring -local p_docent = token("command",P("<!ENTITY")) - * p_optionalwhitespace +local t_docent = token("command",P("<!ENTITY")) + * t_optionalwhitespace * token("keyword",name) - * p_optionalwhitespace + * t_optionalwhitespace * ( ( token("constant",P("SYSTEM")) - * p_optionalwhitespace - * p_docstr - * p_optionalwhitespace + * t_optionalwhitespace + * t_docstr + * t_optionalwhitespace * token("constant",P("NDATA")) - * p_optionalwhitespace + * t_optionalwhitespace * token("keyword",name) ) + ( token("constant",P("PUBLIC")) - * p_optionalwhitespace - * p_docstr + * t_optionalwhitespace + * t_docstr ) + ( - p_docstr + t_docstr ) ) - * p_optionalwhitespace + * t_optionalwhitespace * token("command",P(">")) -local p_docele = token("command",P("<!ELEMENT")) - * p_optionalwhitespace +local t_docele = token("command",P("<!ELEMENT")) + * t_optionalwhitespace * token("keyword",name) - * p_optionalwhitespace + * t_optionalwhitespace * token("command",P("(")) * ( - p_spacing + t_localspacing + token("constant",P("#CDATA") + P("#PCDATA") + P("ANY")) + token("text",P(",")) + token("comment",(1-S(",)"))^1) )^1 * token("command",P(")")) - * p_optionalwhitespace + * t_optionalwhitespace * token("command",P(">")) -local p_docset = token("command",P("[")) - * p_optionalwhitespace - * ((p_optionalwhitespace * (p_docent + p_docele))^1 + token("comment",(1-P("]"))^0)) - * p_optionalwhitespace +local t_docset = token("command",P("[")) + * t_optionalwhitespace + * ((t_optionalwhitespace * (t_docent + t_docele))^1 + token("comment",(1-P("]"))^0)) + * t_optionalwhitespace * token("command",P("]")) -local p_doctype = token("command",P("<!DOCTYPE")) - * p_optionalwhitespace +local t_doctype = token("command",P("<!DOCTYPE")) + * t_optionalwhitespace * token("keyword",name) - * p_optionalwhitespace + * t_optionalwhitespace * ( ( token("constant",P("PUBLIC")) - * p_optionalwhitespace - * p_docstr - * p_optionalwhitespace - * p_docstr - * p_optionalwhitespace + * t_optionalwhitespace + * t_docstr + * t_optionalwhitespace + * t_docstr + * t_optionalwhitespace ) + ( token("constant",P("SYSTEM")) - * p_optionalwhitespace - * p_docstr - * p_optionalwhitespace + * t_optionalwhitespace + * t_docstr + * t_optionalwhitespace ) )^-1 - * p_docset^-1 - * p_optionalwhitespace + * t_docset^-1 + * t_optionalwhitespace * token("command",P(">")) lexer.embed_lexer(xmllexer, lualexer, token("command", openlua), token("command", closelua)) @@ -231,7 +232,7 @@ lexer.embed_lexer(xmllexer, xmlcommentlexer, token("command", opencomment), toke lexer.embed_lexer(xmllexer, xmlcdatalexer, token("command", opencdata), token("command", closecdata)) lexer.embed_lexer(xmllexer, xmlscriptlexer, token("command", openscript), token("command", closescript)) --- local p_name = +-- local t_name = -- token("plain",name) -- * ( -- token("default",colon) @@ -239,11 +240,11 @@ lexer.embed_lexer(xmllexer, xmlscriptlexer, token("command", openscript), toke -- ) -- + token("keyword",name) -local p_name = -- more robust +local t_name = -- more robust token("plain",name * colon)^-1 * token("keyword",name) --- local p_key = +-- local t_key = -- token("plain",name) -- * ( -- token("default",colon) @@ -251,81 +252,82 @@ local p_name = -- more robust -- ) -- + token("constant",name) -local p_key = +local t_key = token("plain",name * colon)^-1 * token("constant",name) -local p_attributes = ( - p_optionalwhitespace - * p_key - * p_optionalwhitespace +local t_attributes = ( + t_optionalwhitespace + * t_key + * t_optionalwhitespace * token("plain",equal) - * p_optionalwhitespace - * (p_dstring + p_sstring) - * p_optionalwhitespace + * t_optionalwhitespace + * (t_dstring + t_sstring) + * t_optionalwhitespace )^0 -local p_open = +local t_open = token("keyword",openbegin) * ( - p_name - * p_optionalwhitespace - * p_attributes + t_name + * t_optionalwhitespace + * t_attributes * token("keyword",closebegin) + token("error",(1-closebegin)^1) ) -local p_close = +local t_close = token("keyword",openend) * ( - p_name - * p_optionalwhitespace + t_name + * t_optionalwhitespace * token("keyword",closeend) + token("error",(1-closeend)^1) ) -local p_entity = +local t_entity = token("constant",entity) -local p_instruction = +local t_instruction = token("command",openinstruction * P("xml")) - * p_optionalwhitespace - * p_attributes - * p_optionalwhitespace + * t_optionalwhitespace + * t_attributes + * t_optionalwhitespace * token("command",closeinstruction) + token("command",openinstruction * name) * token("default",(1-closeinstruction)^1) * token("command",closeinstruction) -local p_invisible = +local t_invisible = token("invisible",invisibles^1) --- local p_preamble = --- token('preamble', p_preamble ) +-- local t_preamble = +-- token("preamble", t_preamble ) xmllexer._rules = { - { "whitespace", p_spacing }, - { "preamble", p_preamble }, - { "word", p_word }, - -- { "text", p_text }, - -- { "comment", p_comment }, - -- { "cdata", p_cdata }, - { "doctype", p_doctype }, - { "instruction", p_instruction }, - { "close", p_close }, - { "open", p_open }, - { "entity", p_entity }, - { "invisible", p_invisible }, - { "rest", p_rest }, + { "whitespace", t_spacing }, + { "preamble", t_preamble }, + { "word", t_word }, + -- { "text", t_text }, + -- { "comment", t_comment }, + -- { "cdata", t_cdata }, + { "doctype", t_doctype }, + { "instruction", t_instruction }, + { "close", t_close }, + { "open", t_open }, + { "entity", t_entity }, + { "invisible", t_invisible }, + { "rest", t_rest }, } xmllexer._tokenstyles = context.styleset xmllexer._foldpattern = P("</") + P("<") + P("/>") -- separate entry else interference ++ P("<!--") + P("-->") -xmllexer._foldsymbols = { -- somehow doesn't work yet +xmllexer._foldsymbols = { _patterns = { "</", "/>", @@ -336,6 +338,13 @@ xmllexer._foldsymbols = { -- somehow doesn't work yet ["/>"] = -1, ["<"] = 1, }, + ["command"] = { + ["</"] = -1, + ["/>"] = -1, + ["<!--"] = 1, + ["-->"] = -1, + ["<"] = 1, + }, } return xmllexer |