summaryrefslogtreecommitdiff
path: root/Master/texmf-dist/tex/context/base/lxml-mis.lua
diff options
context:
space:
mode:
Diffstat (limited to 'Master/texmf-dist/tex/context/base/lxml-mis.lua')
-rw-r--r--Master/texmf-dist/tex/context/base/lxml-mis.lua106
1 files changed, 106 insertions, 0 deletions
diff --git a/Master/texmf-dist/tex/context/base/lxml-mis.lua b/Master/texmf-dist/tex/context/base/lxml-mis.lua
new file mode 100644
index 00000000000..a117b1af92a
--- /dev/null
+++ b/Master/texmf-dist/tex/context/base/lxml-mis.lua
@@ -0,0 +1,106 @@
+if not modules then modules = { } end modules ['lxml-mis'] = {
+ version = 1.001,
+ comment = "this module is the basis for the lxml-* ones",
+ author = "Hans Hagen, PRAGMA-ADE, Hasselt NL",
+ copyright = "PRAGMA ADE / ConTeXt Development Team",
+ license = "see context related readme files"
+}
+
+local concat = table.concat
+local type, next, tonumber, tostring, setmetatable, loadstring = type, next, tonumber, tostring, setmetatable, loadstring
+local format, gsub = string.format, string.gsub
+
+--[[ldx--
+<p>The following helper functions best belong to the <t>lmxl-ini</t>
+module. Some are here because we need then in the <t>mk</t>
+document and other manuals, others came up when playing with
+this module. Since this module is also used in <l n='mtxrun'/> we've
+put them here instead of loading mode modules there then needed.</p>
+--ldx]]--
+
+function xml.gsub(t,old,new)
+ local dt = t.dt
+ if dt then
+ for k=1,#dt do
+ local v = dt[k]
+ if type(v) == "string" then
+ dt[k] = gsub(v,old,new)
+ else
+ xml.gsub(v,old,new)
+ end
+ end
+ end
+end
+
+function xml.strip_leading_spaces(dk,d,k) -- cosmetic, for manual
+ if d and k and d[k-1] and type(d[k-1]) == "string" then
+ local s = d[k-1]:match("\n(%s+)")
+ xml.gsub(dk,"\n"..string.rep(" ",#s),"\n")
+ end
+end
+
+function xml.serialize_path(root,lpath,handle)
+ local dk, r, d, k = xml.first(root,lpath)
+ dk = xml.copy(dk)
+ xml.strip_leading_spaces(dk,d,k)
+ xml.serialize(dk,handle)
+end
+
+--~ xml.escapes = { ['&'] = '&amp;', ['<'] = '&lt;', ['>'] = '&gt;', ['"'] = '&quot;' }
+--~ xml.unescapes = { } for k,v in pairs(xml.escapes) do xml.unescapes[v] = k end
+
+--~ function xml.escaped (str) return (gsub(str,"(.)" , xml.escapes )) end
+--~ function xml.unescaped(str) return (gsub(str,"(&.-;)", xml.unescapes)) end
+--~ function xml.cleansed (str) return (gsub(str,"<.->" , '' )) end -- "%b<>"
+
+local P, S, R, C, V, Cc, Cs = lpeg.P, lpeg.S, lpeg.R, lpeg.C, lpeg.V, lpeg.Cc, lpeg.Cs
+
+-- 100 * 2500 * "oeps< oeps> oeps&" : gsub:lpeg|lpeg|lpeg
+--
+-- 1021:0335:0287:0247
+
+-- 10 * 1000 * "oeps< oeps> oeps& asfjhalskfjh alskfjh alskfjh alskfjh ;al J;LSFDJ"
+--
+-- 1559:0257:0288:0190 (last one suggested by roberto)
+
+-- escaped = Cs((S("<&>") / xml.escapes + 1)^0)
+-- escaped = Cs((S("<")/"&lt;" + S(">")/"&gt;" + S("&")/"&amp;" + 1)^0)
+local normal = (1 - S("<&>"))^0
+local special = P("<")/"&lt;" + P(">")/"&gt;" + P("&")/"&amp;"
+local escaped = Cs(normal * (special * normal)^0)
+
+-- 100 * 1000 * "oeps&lt; oeps&gt; oeps&amp;" : gsub:lpeg == 0153:0280:0151:0080 (last one by roberto)
+
+-- unescaped = Cs((S("&lt;")/"<" + S("&gt;")/">" + S("&amp;")/"&" + 1)^0)
+-- unescaped = Cs((((P("&")/"") * (P("lt")/"<" + P("gt")/">" + P("amp")/"&") * (P(";")/"")) + 1)^0)
+local normal = (1 - S"&")^0
+local special = P("&lt;")/"<" + P("&gt;")/">" + P("&amp;")/"&"
+local unescaped = Cs(normal * (special * normal)^0)
+
+-- 100 * 5000 * "oeps <oeps bla='oeps' foo='bar'> oeps </oeps> oeps " : gsub:lpeg == 623:501 msec (short tags, less difference)
+
+local cleansed = Cs(((P("<") * (1-P(">"))^0 * P(">"))/"" + 1)^0)
+
+xml.escaped_pattern = escaped
+xml.unescaped_pattern = unescaped
+xml.cleansed_pattern = cleansed
+
+function xml.escaped (str) return escaped :match(str) end
+function xml.unescaped(str) return unescaped:match(str) end
+function xml.cleansed (str) return cleansed :match(str) end
+
+function xml.join(t,separator,lastseparator)
+ if #t > 0 then
+ local result = { }
+ for k,v in pairs(t) do
+ result[k] = xml.tostring(v)
+ end
+ if lastseparator then
+ return concat(result,separator or "",1,#result-1) .. (lastseparator or "") .. result[#result]
+ else
+ return concat(result,separator)
+ end
+ else
+ return ""
+ end
+end