Module:ImportProtein explained

local p =

function p.main (frame) ---- Set up the initial frame parameters local debuglog="|}|}" local args=frame.args local parent=frame.getParent(frame) local pargs= if parent then pargs=parent.args end local height=args.height or pargs.height or "50" local width=args.width or pargs.width or "600" local background=args.background or pargs.background or "#333333" local vtext=args.vtext or pargs.vtext or 25 -- characters of legend text to display vertically down from motifs local largeonlyregion=args.largeonlyregion or pargs.largeonlyregion or 20 local vtext=tonumber(vtext) -- no meaning except as a number local tableoutput=args.tableoutput or pargs.tableoutput or "mw-collapsed" -- I've decided to use the table as the legend much of the time after all, I think. (previously defaulted to "nil" to suppress) if tableoutput

"no" then tableoutput=nil end local vwidth=args.vwidth or pargs.vwidth or 4 -- number of PIXELS to tag as not overwriteable with vertical text. local vclaim= --- if vclaim[pixel] is true, that pixel is taken local vprotest= --- list of positions not shown separated by spaces local nowiki=args.nowiki or pargs.nowiki ---- These parameters send text that needs to be processed into tables ---- include is nil to include everything. If it exists then only what is in it is used. ---- format is "I want only this" (any junk) "and this" etc. Note weakness - a stray quote would foul up the whole template. local include=args.include or pargs.include or "all" if include

"all" then include = nil end local tinclude= if include then for i in mw.ustring.gmatch(include,%"(.-)%") do tinclude[i]=1 end end ---- replaceregion defines a section with too many features to note individually. ---- Instead you group them with a new text. ---- The format is xx..yy:"Use this text" local replaceregion=args.replaceregion or pargs.replaceregion or "" local treplaceregion= treplaceregion.s=;treplaceregion.e=;treplaceregion.t= for i,j,k in mw.ustring.gmatch(replaceregion,) do table.insert(treplaceregion.s,tonumber(i));table.insert(treplaceregion.e,tonumber(j));table.insert(treplaceregion.t,tostring(k)) end ---- exclude "Forget about this" (junk between ignored). ---- this prevents things from showing up even in the table and all motifs of this kind local exclude=args.exclude or pargs.exclude or "" -- for these empty arrays will be ignored later. local texclude= for i in mw.ustring.gmatch(exclude,%"(.-)%") do texclude[i]=1 end ---- usenotes "This is a crummy motif name" (junk between ignored). Uses /note entries instead local usenotes=args.usenotes or pargs.usenotes or "" local tusenotes= for i in mw.ustring.gmatch(usenotes,%"(.-)%") do tusenotes[i]=1 end ---- substitute "Don't like this wording":"That's what I want" (anything between these ignored) local substitute=args.substitute or pargs.substitute or "" local tsubstitute= for i,j in mw.ustring.gmatch(substitute,) do tsubstitute[i]=j end ---- toprow "Put this motif in the top row, no vertical annotation" ---- If present, defines an upper part of the graphic to mark certain features by color only - most likely, helices and sheets and turns local toprowtext=args.toprow or pargs.toprow or "" local ttoprow= local toprowheight=0 -- no height unless one exists local toprow -- boolean to mark if anything is actually on the top row for i in mw.ustring.gmatch(toprowtext,%"(.-)%") do ttoprow[i]=1;toprow=true end if toprow then toprowheight=args.toprowheight or pargs.toprowheight or 10 end ---- Check there is a protein sequence file and figure out where the CDS in it starts and ends local file=args.file or pargs.file if not(file) then return "error: use 'file=some cut-and-pasted NCBI protein sequence' to input a protein to be diagrammed" end local cdsstart, cdsend = mw.ustring.match(file,"Protein%s-(%d+)%.%.(%d+)") cdsstart=tonumber(cdsstart);cdsend=tonumber(cdsend) if ((cdsstart<1) or (cdsend<1)) then return end local cdswidth=cdsend-cdsstart ---- Find and replace Site and Region to create unique separators ---- so that every one of these sections can be individually processed in the main loop file = mw.ustring.gsub(file,"Site%s+","|##|S") -- there are no pipe characters in the input or it would have choked file = mw.ustring.gsub(file,"Region%s+","|##|R") file = mw.ustring.gsub(file,"$","|##|") --- close last feature at the EOF ---- Load a set of colors to use for the different motifs. ---- Any unicode separator changes them. No format expectations. local colorpage=mw.title.new("Template:ImportProtein/DefaultColors") local content local color= if colorpage then content=colorpage.getContent(colorpage) if content then for x in mw.ustring.gmatch(content,"(%S+)") do table.insert(color,x) end end end if #color<1 then color= end local claim=;local nextcolor=1 -- keeps track of the colors assigned to specific nkeys throughout the loop ---- Begin the output and graphics files local output local tlegend="" -- legend for top row entries only, shown above table if tableoutput

"collapsed" then output=class="wikitable mw-collapsible mw-collapsed" style="width:]].. width .. px;" .. "\n" .. List of protein features .. "\n" .. - elseif tableoutput

"collapsible" then output=class="wikitable collapsible" style="width:]].. width .. px;" .. "\n" .. List of protein features .. "\n" .. - else output=class="wikitable"]] end local graphics=.. background .. .. width .. .. height .. px;"> ---- MAIN LOOP ---- ---- this goes through features one by one and marks them down in "output" (legend/table) and "graphics" (protein box and vertical annotation) ---- Note that this does NOT create an array of features to sort, but is purely once through. ---- This means, for example, that there is no easy way to reposition adjacent motifs left and right to fit automatically. ---- You could, of course, array the output and retroactively process it ... maybe even turn this into a sortable array of function tail calls??? (My head hurts) for feature, range in mw.ustring.gmatch(file,"#|(.-)|#") do local t=mw.ustring.match(feature,"^(%a)") -- S or R placed in previous find/replace local s=mw.ustring.match(feature,"(%d+)") -- first number is the beginning of site or region local e=mw.ustring.match(feature,"^.%s-%d+%.%.(%d+)") or s -- second number in xx..yy range ; this needs updating! if s then ---- decide on the name to be used for the motif and annotation local n,c if t

"R" then n=mw.ustring.match(feature,/region_name=%"(.-)%") end if t

"S" then n=mw.ustring.match(feature,/site_type=%"(.-)%") end n=tostring(n) if tusenotes[n] then n=mw.ustring.match(feature,/note=%"(.-)%") or n end n=tostring(n) n=mw.ustring.match(n,"^%s+(.+)%s+$") or n -- kill white space n=mw.ustring.gsub(n,"\n"," ") or n -- remove line feeds n=tostring(n) -- am I paranoid? if tsubstitute[n] then n=tostring(tsubstitute[n]) end n = mw.ustring.match(n,"(.+)%.") or n -- Don't need the ubiquitous final periods ---- from the name (n) pull out an nkey that excludes parenthesized stuff ---- each unique nkey can claim its own color to use from here on out local nkey=mw.ustring.match(n,"(.+)[%.;,%(%[]") or n local newcolor=false; -- is this a new color (if so, then if it is toprow, then add to legend for those) if claim[nkey] then c=claim[nkey] else c=color[nextcolor];claim[nkey]=c;nextcolor=nextcolor+1;newcolor=true end local cstyle= .. c .. ---- decide whether to show the motif, and crop it to the CDS local showthismotif=true s=tonumber(s);e=tonumber(e) if scdsend then e=cdsend end if s

cdsstart and e

cdsend then showthismotif=nil end if include and not tinclude[n] then showthismotif=nil end -- if include is set, and n isn't in it, don't add to table or graphic if exclude and texclude[n] then showthismotif=nil end -- if exclude is set and n is in it don't add if showthismotif then ---- update the table output for the legend if tostring(t)

"R" then output = output .. "\n|" .. cstyle .. "region\n|" else output = output .. "\n|" .. cstyle .. "site\n|" end output = output .. cstyle .. tostring(s) .. "\n|" .. cstyle .. tostring(e) .. "\n|" .. cstyle .. n .. "\n|-" ---- update the graphic display: first determine if the block is large to be displayed full height and annotated inside itself nkey=mw.ustring.sub(nkey,1,vtext) -- for graphics purposes, truncate the string (default 25 characters) local large local boxleft=math.floor(width*tonumber(s)/cdswidth) local boxwidth=math.floor(width*tonumber(e)/cdswidth)-boxleft if boxwidth>8*tonumber(mw.ustring.len(nkey)) then large=true else large=nil end ---- then work out the horizontal or vertical display local vertical -- height substring of the drawn block local annot="" -- text contents of a large block if ttoprow[n] then vertical=tostring(toprowheight) if newcolor then tlegend=tlegend.. .. c ..

">  

.. nkey .. "\n" end nkey="" else if large then vertical=tostring(height-toprowheight) if toprow then vertical=vertical .. "px;top:" .. tostring(toprowheight) end annot="" .. nkey .."" nkey="" -- no vertical text display else vertical=tostring(math.floor(height) - toprowheight - largeonlyregion) .. "px;top:" .. tostring(toprowheight + largeonlyregion) nkey=mw.ustring.gsub(nkey,"(.)","%1
") -- verticalize the text end end local z=10000-1*boxwidth --- smaller elements in front of larger ones if not(large) then z=z+10000 end --- large elements reliably to the back -- draw graphics within the protein rectangle graphics = graphics .. .. z .. .. boxleft .. .. c .. .. c .. .. boxwidth .. .. vertical .. .. annot ..