Generate an inventory of file types found in a filesystem

file_type_inventory.R

pacman::p_load(
  readr,
  httr,
  jsonlite,
  curl,
  stringr,
  dplyr,
  xtable,
  formattable,
  htmlTable,
  data.table,
  RCurl,
  plotly,
  scales,
  SparkR
) # load modules

setwd("~/images/24bit")

######################
## mime types table ##
## editable table used to match file extetions with likely format types

mimeTypes <-
  getURI(
    "https://docs.google.com/spreadsheets/d/e/2PACX-1vQjkkqveEW5eiuO2D_rLIiEs1Whj0Y98m8aIxaKP4qetCebpdYkuW5_4awHcjI0V6DtE3vJ5-ftZJTE/pub?gid=789984673&single=true&output=csv"
  )
mimeTypes <- read.csv(textConnection(mimeTypes))

save(mimeTypes, file = "mimeTypes.Rda")

mimeTypes$Extension <-
  trimws(mimeTypes$Extension) # trim any unseen whitespace
mimeTypes$Extension <- tolower(mimeTypes$Extension)
## mime types table ##
######################

#########################
## targeted files list ##
## make a list of all files in that have a dot-suffix where the suffix is 1 to 5 chars long
fileList <- list.files(
  recursive = TRUE,
  # path = ".",
  all.files = TRUE,
  full.names = FALSE,
  include.dirs = FALSE,
  # pattern = ".*",
  pattern = ".*\\.\\w{1,5}$",
  ignore.case = TRUE
)
## targeted files list ##
#########################

#########################
## ingnored files list ##
ignored.fileList <- as.data.frame(list.files(
  recursive = TRUE,
  # path = ".",
  all.files = TRUE,
  full.names = FALSE,
  include.dirs = FALSE,
  pattern = ".*",
  # pattern = ".*\\.\\w{1,5}$",
  ignore.case = TRUE
)) # make a list of all files

colnames(ignored.fileList) <- "Extension"

ignored.fileList <- ignored.fileList %>%
  filter(grepl(".*\\.\\w{1,5}$",Extension) == FALSE) # remove entries that match 'targeted' list
## ingnored files list ##
#########################

len.fileList <- length(fileList)
len.fileList

extList <- as.data.frame(gsub(".*(\\.\\w{1,5}$)", "\\1", fileList))

len.extList <- length(extList)
len.extList

colnames(extList) <- "Extension"

extList$Extension <-
  trimws(extList$Extension) # trim any unseen whitespace

extList$Extension <- tolower(extList$Extension)

files.found <-
  merge(
    x = extList,
    y = mimeTypes,
    by.x = "Extension",
    all.x = TRUE,
    ignore.case = TRUE,
    all.y = FALSE,
    incomparables = NA
  )

tbl.ext.counts <- count(files.found,Extension) ; tbl.ext.counts

colnames(tbl.ext.counts) <- c("Extension","Count")

tbl.ext.counts <- merge(
  x = tbl.ext.counts,
  y = mimeTypes,
  by.x = "Extension",
  all.x = TRUE,
  ignore.case = TRUE,
  all.y = FALSE,
  incomparables = NA
)

tbl.ext.counts <- tbl.ext.counts %>%
  arrange(desc(Count))

###################
## mystery files ##
blanks <- files.found %>%
  filter(is.na(Name) == TRUE)

blanks <- count(blanks,Extension) ; blanks
colnames(blanks) <- c("Extension","Count")

blanks <- blanks %>%
  arrange(desc(Count))
## mystery files ##
###################