include("WBInclusions") APFS = "210" # WBSearch:APFS version = APFS global PRE = 20 global POST = 38 global FILTER = nothing global FILTERED = false global MATCHES = [] global PUTS = "" global ARGZ = copy(ARGS) global ARGZlen = length(ARGZ) if ARGZlen > 0 && ARGZ[1][1:1] == "#" len = length(ARGZ[1]) EMP("global FILTER = " * RRead(ARGZ[1][2:len], "asis")) global ARGZ = ARGZlen == 1 ? [] : ARGZ[2:ARGZlen] global FILTERED = true global ARGZlen -= 1 end if ARGZlen == 0 println("\n WBSearch [ \"%%x%\" for 1:'^', 2:'>', 3:'&', 4:'|', 5:'&#' ] v" * APFS * "\n\n RegEx_string [before(", PRE, ") after(", POST, ")] [case-sensitive?]") exit(0) end for itm in ["%%1%" => "^", "%%2%" => ">", "%%3%" => "&", "%%4%" => "&#", "%%5%" => "|" ] ARGZ[1] = replace(ARGZ[1], itm) end if length(ARGZ) > 2 global PRE = parse(Int32, ARGZ[2]) global POST = parse(Int32, ARGZ[3]) end global WC = Dict{String, Int32}() global WCequals = Dict{String, Int32}() global WCcount = 0 global WChcount = 0 global C9s = [] global C9imageDict = Dict{String, Any}() global nowww = noww() # if (h >= "Α" && h <= "Ω") || (h >= "α" && h <= "ω") # Don't trust Greeks! global excludeds = ["Α", "Β", "Γ", "Δ", "Ε", "Ζ", "Η", "Θ", "Ι", "Κ", "Λ", "Μ", "Ν", "Ξ", "Ο", "Π", "Ρ", "΢", "Σ", "Τ", "Υ", "Φ", "Χ", "Ψ", "Ω", "α", "β", "γ", "δ", "ε", "ζ", "η", "θ", "ι", "κ", "λ", "μ", "ν", "ξ", "ο", "π", "ρ", "ς", "σ", "τ", "υ", "φ", "χ", "ψ", "ω", " ", "!", """, "#", "'", "(", ")", "*", "-", "/", ":", "<", "=", ">", "Y", "[", "]", "e", "h", "j", "n", "r", "{", "|", "}"] global t = time(); global gotsomething = false global SZ = Dict{String, String}() global HSYMS = [] global HSYMCT = 0 global WorkString = "" global CCT = 1 global MAXL = 0 global AgeDistribution = Dict{String, Int32}() #global isWIN = Sys.iswindows() #if isWIN # pwwd = pwd() # pwws = findlast("\\", pwwd) # global SOSOSO = pwwd[pwws.start + 1:length(pwwd)] * "\\" #else global SOSOSO = "" #end function et() return formatDecimal(time() - t, 3) end OUTPUTFILE = "JUNK.html" #isWIN ? pwd() * "\\..\\JUNK.html" : "JUNK.html" OUTPUTFILE2 = "JUNK2.html" #isWIN ? pwd() * "\\..\\JUNK2.html" : "JUNK2.html" OUTPUTFILE7 = "JUNK7.html" #isWIN ? pwd() * "\\..\\JUNK7.html" : "JUNK7.html" global searchString = ARGZ[1] global ACCUMS = zeros(Int32, 1) global searchString = ARGZlen == 2 || ARGZlen == 4 ? Regex(searchString) : Regex(searchString, "i") global strs = open("JUNK3.txt", "a") write(strs, nowww * " " * string(searchString) * "\n") close(strs) global errId = 0 global ctr = 0 global cctr = 0 global out = "\n" try global errId = 1 if FILTER == nothing global FILTER = readdir() end global errId = 2 for itm in FILTER itmLen = length(itm) if !isfile(itm) || itmLen < 6 || itm[itmLen - 4 : itmLen] != ".html" || itm in ["XXXRTree.html", "XXXXTree.html" , "XXXTree.html", "JUNK.html", "JUNK2.html", "JUNK6.html", "JUNK7.html", "JUNK10.html"] continue end global item = itm global errId = 4 res = RRead(item, "asis") lenRes = length(res) if lenRes > 49999 lenRes = " " * string(lenRes) lenLenRes = length(lenRes) chk = lenRes[lenLenRes - 10 : lenLenRes] if get(SZ, chk, "GKW") != "GKW" println("Error: " * chk * " " * item) # Program breaks if 2 files same len exit(16) end SZ[chk] = item end c9s = findall(r" href=\"c9/[^\"]+\"", res) for c9 in c9s push!(C9s, [res[c9], item]) end c9s = findall(r" (src|href)=\"c9/[^\"]+\"", res) for c9 in c9s rr = res[c9] if !contains(rr, ".html") r = replace(replace(rr, r" (src|href)=\"c9/" => ""), "\"" => "") a = get(C9imageDict, r, "NUTHIN") if a == "NUTHIN" C9imageDict[r] = Dict{String, Int32}(item => 1) else aa = get(a, item, "NUTHIN") if aa == "NUTHIN" a[item] = 1 else a[item] = a[item] + 1 end end end end WC0 = findall(r"[ \n][a-zA-Z-]+", res) for wc in WC0 s = lowercase(res[wc]) sstop = wc.stop s = s[2 : length(s)] rs1 = res[sstop + 1: sstop + 1] if rs1 == "=" || (rs1 == ":" && s in ["background-color", "border", "border-collapse", "border-radius", "color", "direction", "font-family","font-size", "font-weight", "height", "line-height", "margin", "padding", "text-align", "text-decoration", "vertical-align", "white-space", "width"]) global WChcount += 1 s *= rs1 a = get(WCequals, s, 0) WCequals[s] = a + 1 else global WCcount += 1 a = get(WC, s, 0) WC[s] = a + 1 end end global ctr += 1 if ctr % 50 == 0 ctrr = " " * string(ctr) lenCtrr = length(ctrr) println(ctrr[lenCtrr - 4 : lenCtrr] , " " , et()) end txt = res # String(res) # global zzzzzz = txt # " +2022.04.30 v002 " yyyyyy = findall(r">\+[0-9][0-9][0-9][0-9]\.[0-9][0-9]\.[0-9][0-9] v[0-9][0-9][0-9]", txt) if length(yyyyyy) != 1 && !(item == "Experiment.html" && length(yyyyyy) == 3) # KLUDGE println("Versioning wrong in file: " * item) exit(16) end age = txt[yyyyyy[1]][3:11] if age[9:9] == "3" # Merge dom 30, 31 into 20's age = age[1:8] * "2" end if get(AgeDistribution, age, "NO") != "NO" AgeDistribution[age] += 1 else AgeDistribution[age] = 1 end x = findall(r"&#[^;]+;", txt) global HSYMCT += length(x) for y in x z = txt[y] if length(y) > 10 println(" MESS in ", itm , ": ", hilite(HI_RED, "STARTMESS"), "\"", z , "\"", hilite(HI_RED, "ENDMESS"), "\n") end if z in HSYMS continue end push!(HSYMS, z) end global cctr += length(txt) quotes = "" ct = 1 s = searchString qqk = findall(s, txt) qq = length(qqk) for itm in qqk alpha = itm.start - PRE omega = itm.stop + POST if alpha < 1 omega -= alpha - 1 alpha = 1 end if omega > length(txt) omega = length(txt) end bailout = false global tq = txt[alpha:omega] for i = 1 : length(tq) global ii = Int32(Char(tq[i])) if ii > 127 println("Fuckup: " , item , " \"", tq, "\" " , ii, " \"" , tq[i] , "\"") bailout = true tq = "?" * replace(tq, r"[;&<>']" => "?") * "?" break end end if !bailout aaw = findfirst(s, tq) tq = tq[1 : aaw.start - 1] * "WQWQWQ" * tq[aaw.start : aaw.stop] * "XQXQXQ" * tq[aaw.stop + 1: length(tq)] tq = replace(tq, ";" => "!!!!!!!!#59;") tq = replace(tq, "&" => "&") tq = replace(tq, "!!!!!!!!" => "&") tq = replace(tq, "<" => "<") tq = replace(tq, ">" => ">") tq = replace(tq, "\"" => """) tq = replace(tq, "'" => "'") tq = replace(tq, "/" => "/") tq = replace(tq, "{" => "{") tq = replace(tq, "}" => "}") tq = replace(tq, " " => " ") tq = replace(tq, "WQWQWQ" => "", count=1) # Underscore the search text! tq = replace(tq, "XQXQXQ" => "", count=1) end inf = "
" * string(ct) * ". " * string(itm) global shitfuckshit = 22 if length(inf) > 21 println("\n Inf problem in ", item, ": " * string(length(inf)) * " \"" * inf * "\"\n") global shitfuckshit = 24 end quotes *= inf * (" " ^ (shitfuckshit - length(inf))) * "" * tq * "" ct += 1 end global ACCUMS += [qq] if quotes != "" L = length(item) - 5 if L > MAXL global MAXL = L end global WorkString *= (WorkString == "" ? "" : ", ") * item[1:L] push!(MATCHES, item) global PUTS *= "put " * item * "\n" global out *= "\n" * string(CCT) * ". " * item[1:length(item) - 5] * "  " * quotes * "\n" global out = replace(out, "OSOSOS" => SOSOSO) global gotsomething = true global CCT += 1 end end catch ex s = string(ex) if length(s) > 200 s = s[1:200] * "..." end println("\nDoing: " * item * " \"" * tq * "\"") println(" Failure[" * string(errId) * "]: ", typeof(ex), ".\n", s); exit(16) end hsyms = [] hsyms2 = [] global k = 1 global gotSomething = false for i = 1 : length(HSYMS) h = HSYMS[i] if h in excludeds # Don't trust Greeks! continue end if k % 10 == 1 if gotSomething kn1 = k - 1 sp = "[" * string(kn1) * "]" push!(hsyms, sp) sp = "[" * string(kn1) * "]" push!(hsyms2, sp) gotSomething = false end end push!(hsyms, h) push!(hsyms2,h[3 : length(h) - 1]) global k += 1 global gotSomething = true end sct = formatFixed(HSYMCT) global out *= (gotsomething ? "" : "\n[No matches]  \n") * "

 

\n" * "

" * string(k - 1) * ":  " * replace(join(hsyms, ", "), ", [" => " [") * "

" * "

" * string(k - 1) * ":  " * replace(replace(join(hsyms2, ", "), ", [" => " ["), "x" => "x") * "  [Σ " * sct * "]

\n" * "JUNK2.html  JUNK3.txt  JUNK7.html" * "

PUTS | MATCHES  (" * string(MAXL) * ") \"" * WorkString * "\"



\n
\"This
" stotlen = string(cctr) if cctr> 999 stotlen = stotlen[1:length(stotlen) - 3] * "," * stotlen[length(stotlen) - 2 : length(stotlen)] end if cctr > 999999 stotlen = stotlen[1:length(stotlen) - 7] * "," * stotlen[length(stotlen) - 6 : length(stotlen)] end pre = "\nFrustra\n

" s = Array{Any}(undef, 1 * 2 + 1) s[1] = " " global ix = 2 println(" searchString: ", hilite(HI_AQUA, "| "), searchString , hilite(HI_AQUA, " |"), ".") ss = searchString s[ix] = ss global ix = ix + 1 s[ix] = " " global ix += 1 s = replace(replace(string(s), "<" => "<"), ">" => ">") sp = "" s = replace(s, "Any[" => "Any[ ") s = replace(s, "\" \", " => "  ") s = replace(s, ", \" \"" => "   ") s = replace(s, "Any[   r\"" => "Any[   r\"" * sp) s = replace(s, "\"i,   r\"" => "\"i,   r\"" * sp) s = replace(s, r"\"(i?)   " => s"\"\1   ") pre *= "[ \"%%x%\" for 1:'^', 2:'>', 3:'&', 4:'&#', 5:'|' ]  " * s * ".  " * OUTPUTFILE pre *= "
Files: " * string(ctr) * ".  Chars: " * stotlen * ".  Σ" * string(ACCUMS) * string(CCT - 1) * "  Time: " * et() * ".  v" * version * "      " * replace(APtS_ET, r"d([^m]+)m" => s"d\1s") * (FILTERED ? "    FILTERED!" : "") * "

" z = open(OUTPUTFILE, "w") write(z, pre * out) close(z) kk = keys(SZ) szfuxk = [] for k in kk push!(szfuxk, string(k)) end global fu = "" szfuxk = sort(szfuxk, rev = true) global fx = " 3" global FU66 = " " for f in szfuxk if f[6:6] != FU66 # fx[6:6] != " " && f[6:6] == " " global fu *= "\n" global fx = " " * f[6:6] global FU66 = f[6:6] end global fu *= f * " " * SZ[f] * "\n" end fuLen = length(szfuxk) kk = keys(AgeDistribution) szfuxk = [] for k in kk push!(szfuxk, string(k)) end szfuxk = sort(szfuxk, rev = true) global pf1 = "" global pf2 = "" global you = "" global totAges = 0 for f in szfuxk ct = " " * string(AgeDistribution[f]) global totAges += AgeDistribution[f] lenCt = length(ct) newf = "" if f[1:4] == pf1 newf = " " else global pf1 = f[1:4] newf = pf1 end newf *= " " if f[6:7] == pf2 newf *= " " else global pf2 = f[6:7] newf *= pf2 end newf *= " " * f[9:9] shitshit = ct[lenCt - 5 : lenCt] global you *= "\n " * newf * shitshit end global totAgess = " " * string(totAges) global lenTA = length(totAgess) global you *= "\n ----------\n " * totAgess[lenTA - 5 : lenTA] z = open(OUTPUTFILE2, "w") write(z, "\n\n\nFrustra\n") write(z,"\n") write(z,"\n\n
\n

C:\\ROM\\JUNK2.html

\n
\n")
zn = string(now())
zn = zn[1:10] * " " * zn[12 : length(zn)] 
write(z, "    WBSearch v" * version * "(j:" * string(VERSION) * ")   [ \"%%x%\" for 1:'^', 2:'>', 3:'&', 4:'&#', 5:'|' ]   " * APtS_ET * "\n")
fu2 = replace(fu, r" ([0-9]+)   ([^ .]+)\.html" =>
                  s" \1   \2.html")

fu2 = replace(fu2, "OSOSOS" => SOSOSO)
write(z, "    " * zn * "  (" * string(fuLen) * "\n" * fu2)
write(z, you)
write(z, "
\n
\n") write(z, "\n" ) global tr = "" C9ss = sort(C9s, by = x -> lowercase(x[1] * x[2])) FU = Dict() for c9 in C9ss if get!(FU, c9, "SHIT") == "SHIT" FU[c9] = 1 else FU[c9] += 1 end end SHIT = [] for k in keys(FU) push!(SHIT, string(k)) end ASSHOLE0 = [] for shit in keys(FU) push!(ASSHOLE0, [shit[2] * shit[1], [shit[1], shit[2], FU[shit]]]) end ASSHOLE = sort(ASSHOLE0, by = x -> lowercase(x[1])) global tr = "c9/" global ix = 0 for shit0 in ASSHOLE shit = shit0[2] write(z, "" * shit[2] * "" * tr * "" * shit[1][11 : length(shit[1]) - 1] * "" * string(shit[3]) * "\n") global tr = " " global ix += 1 end write(z, "\n") write(z, "
\"This
\n
\n") close(z) println("\nOutput saved to: " * OUTPUTFILE* ". Σ" * string(ACCUMS) * string(CCT - 1) * "\nv" * version * ". Time: " * et()) function gsk(x) x2 = x[2] lenx2 = length(x2) if (lenx2 = length(x2)) > 3 return x[1] * 276922881 + # powers of 129 Int32(x2[1]) * 2146689 + Int32(x2[2]) * 16641 + Int32(x2[3]) * 129 + Int32(x2[4]) end if lenx2 == 3 return x[1] * 276922881 + Int32(x2[1]) * 2146689 + Int32(x2[2]) * 16641 + Int32(x2[3]) * 129 end if lenx2 == 2 return x[1] * 276922881 + Int32(x2[1]) * 2146689 + Int32(x2[2]) * 16641 end return x[1] * 276922881 + Int32(x2[1]) * 2146689 end function WCf(dict) WCS = [] for k in keys(dict) v = dict[k] push!(WCS, [v,string(k)]) end return sort(WCS, by = x -> gsk(x), rev=true) end global info = replace(replace(replace(replace(replace(replace(replace(replace(replace(replace(replace(string(WCf(WC)), r"Any\[(\d+). \"([^\"]+)\"\][,\]] ?" => s"\n\1 \2"), r"^Any\[" => ""), r"\n(\d{4}) " => s"\n \1 "), r"\n(\d{3}) " => s"\n \1 "), r"\n(\d{2}) " => s"\n \1 "), r"\n(\d) " => s"\n \1 ", count = 1), r"\n (\d{4}) " => s"\n \n \1 ", count=1), r"\n (\d{3}) " => s"\n \n \1 ", count=1), r"\n (\d{2}) " => s"\n \n \1 ", count=1), r"\n (\d) " => s"\n \n \1 ", count=1), r"\n(\d) " => s"\n \1 ") # I do not understand why I need this translation global info *= "

Equals and colons (" * formatFixed(length(WCequals)) * "):

\n
\n"

global brk = 77
global frst = true
WCSS = WCf(WCequals)
vlen = length(WCSS)
for i = 1 : vlen
    v = WCSS[i]
    v1 = string(v[1])
    lenv = length(v1)
    if lenv != brk
        if !frst
            global info *= " \n"
        end
        global frst = false
        global brk = lenv
    end
    global info *= " " ^ (5 - lenv) * v1 * "  " *  v[2]  * "\n"
end

z = open(OUTPUTFILE7, "w")
write(z, "\n\n\nFrustra\n\n
\n
C:\\ROM\\JUNK7.html    X3  X2  X1 EC\"Next\"
\n
" *
noww() * "  v" * APFS *    
    ".    Unique words: " * formatFixed(length(WC)) *
    ".   Total words:  Text: " * formatFixed(WCcount) *
    ",  HTML: " * formatFixed(WChcount) *
    "
\n
\n")
zn = string(now())
zn = zn[1:10] * " " * zn[12 : length(zn)] 
write(z, "WBSearch v" * version * "(j:" * string(VERSION) * ")   [ \"%%x%\" for 1:'^', 2:'>', 3:'&', 3:'&', 4:'&#', 5:'|' ]   " * APtS_ET * "\n")
fu2 = replace(fu, r" ([0-9]+)   ([^ .]+)\.html" =>
                  s" \1   \2.html")
write(z, info)
write(z, "
\n
\n
\"This
\n
\n")
close(z)

a = open("C9IMAGDICT", "w")
write(a, string([noww() * "  v" * version, C9imageDict]))
close(a)
a = open("MATCHES", "w")
write(a, string(MATCHES))
close(a)
a = open("PUTS", "w")
write(a, PUTS)
close(a)

println("       Time: " * et())