“c_cs_alpha.pdf” was downloaded from https://www.deadiversion.usdoj.gov/schedules/orangebook/c_cs_alpha.pdf on 2020-09-08
“DIR-020-17 Drug Slang Code Words.pdf” was downloaded from https://www.dea.gov/ on
2020-09-08 but the full path (documents/2017/05/01) no
longer exists. We believe the original file can be found here: https://www.dea.gov/sites/default/files/2018-07/DIR-020-17%20Drug%20Slang%20Code%20Words.pdf.
Note that the file name was changed to remove the spaces (which appear
as %20) in the link above.
library(pdftools)
x <- pdf_text("../inst/extdata/DIR-020-17DrugSlangCodeWords.pdf")
sink("slang.txt")
cat(x[2:7])
sink()Opened with Ultra Edit Edited text file to remove headers Used Format: Convert Line Terminator to Wrap
library(readr) # read_delm
s <- read_delim("../inst/extdata/slangUE.txt", "~", escape_double = FALSE,
col_names = c("category", "brand", "slang"),
col_types = cols(
category = col_character(),
brand = col_character(),
slang = col_character()),
trim_ws = TRUE)
library(tidyr) # for separate_rows()
library(stringr) #str_squish
suppressPackageStartupMessages(library(dplyr)) # mutate %>%
dea_street_names <- separate_rows(s, slang, sep = ";") %>%
mutate(slang = str_squish(slang)) %>%
distinct() # Blaze listed twice in Synthetic Cannabinoids