embed 1

NAMESPACE

@@ -5,6 +5,7 @@ export(hash_compare)
 export(hash_con)
 export(hash_file)
 export(hash_raw)
+export(split_hash)
 importFrom(Rcpp,sourceCpp)
 importFrom(magrittr,"%>%")
 useDynLib(ssdeepr, .registration = TRUE)

R/hash-file.R

@@ -14,12 +14,12 @@
 #' hash_compare(hashes$hash[1], hashes$hash[4])
 hash_file <- function(path) {
 
-  path <- path.expand(path)
-
   lapply(path, function(.x) {
 
-    if (file.exists(.x)) {
-      hash <- int_hash_file(.x)
+    xpath <- path.expand(.x)
+
+    if (file.exists(xpath)) {
+      hash <- int_hash_file(xpath)
     } else {
       hash <- NA_character_
     }

R/split-hash.R

@@ -0,0 +1,28 @@
+#' Splits an ssdeep hash string into component parts
+#'
+#' ssdeep hashes consists of three parts, separated by `:`:
+#' - chunk size : size of the chunks in rest of the hash
+#' - chunk : where each character represents a part of the file of length "chunk size"
+#' - double chunk : hash computation where "chunk size" = 2 * "chunk size"
+#' This function splits the single has string into three component parts.
+#'
+#' @param x character vector of ssdeep hashes
+#' @return data frame
+#' @export
+#' @examples
+#' split_hash(hash_con(url("https://en.wikipedia.org/wiki/Donald_Knuth")))
+split_hash <- function(x) {
+
+  components <- strsplit(x, ":", fixed = TRUE)
+  lapply(components, function(.x) {
+    as.data.frame(as.list(setNames(.x, c("chunk_size", "chunk", "double_chunk"))), stringsAsFactors = FALSE)
+  }) -> out
+
+  out <- do.call(rbind.data.frame, out)
+  class(out) <- c("tbl_df", "tbl", "data.frame")
+
+  out[["chunk_size"]] <- as.integer(out[["chunk_size"]])
+
+  out
+
+}

man/split_hash.Rd

@@ -0,0 +1,26 @@
+% Generated by roxygen2: do not edit by hand
+% Please edit documentation in R/split-hash.R
+\name{split_hash}
+\alias{split_hash}
+\title{Splits an ssdeep hash string into component parts}
+\usage{
+split_hash(x)
+}
+\arguments{
+\item{x}{character vector of ssdeep hashes}
+}
+\value{
+data frame
+}
+\description{
+ssdeep hashes consists of three parts, separated by \code{:}:
+\itemize{
+\item chunk size : size of the chunks in rest of the hash
+\item chunk : where each character represents a part of the file of length "chunk size"
+\item double chunk : hash computation where "chunk size" = 2 * "chunk size"
+This function splits the single has string into three component parts.
+}
+}
+\examples{
+split_hash(hash_con(url("https://en.wikipedia.org/wiki/Donald_Knuth")))
+}