wff_dict_verbose.jl

#!/usr/local/bin/julia -i
# header not necessary, allows one to call
#   ./wff1.jl ARGS...
# after chmod +x wff1.jl

# Alternatively call
#   julia -i wff1.jl
# the -i denotes "interactive mode" similar to the cli in python.
# to just execute the code omit -i
5
const DEF = "tests/one.txt"

if length(ARGS) > 0 # ARGS is an array of command line arguments as strings (separated by spaces)
    files = ARGS[1:end] # indexing starts at 1!
else
    println("please provide at least one file name!")
    println("RUNNING $DEF")
    files = [DEF]
end

# instantiate a dictionary of dictionaries
# one dictionary for each file provided, with the file name as key
word_dicts = Dict(file=>Dict{String, Int}() for file in files) # optional typing
delims = [' ','\n','\t','.',',','(',')','?','/'] # single quotes: character literal

for file in files
    println("reading $(file)") # string interpolation (parentheses not necessary)!
    open(file) do f # alternatively, f = open(file), just have to remember close(f) when done
        s = readstring(f) # read entire contents as string
        for word in split(s,delims) # split string by literals in array 'delims'
            if haskey(word_dicts[file], word) # check if word has already been seen
                word_dicts[file][word] += 1 # if so, increment counter
            else
                word_dicts[file][word] = 1 # otherwise add word as key with value 1
            end
        end
    end
end

# print word frequencies for each file
for file in files
    println("\nword frequencies for $file") # linebreak (\n) interpolation
    for kv in word_dicts[file]
        println("\t$(kv)") # tab (\t) interpolation
    end
end

println("\n --------------------------------------------------------------------")
println("\nyou are now in interactive mode!")
println("enter `word_dicts` in the command line to view your dictionary in REPL")
println("\tlooking up key values is the same syntax as indexing")
println(" e.g. `word_dicts[\"$(files[1])\"]` is the dictionary of word frequencies for `$(files[1])`")
println("\n --------------------------------------------------------------------\n")
println("enter `exit()` to ESCAPE\n")