## ----setup, include=FALSE-----------------------------------------------------
knitr::opts_chunk$set(collapse = TRUE, comment = "#>", warning = FALSE, message = FALSE)
library(mudnester)

## ----detect-demo--------------------------------------------------------------
patient_data <- data.frame(
  patient_name = c("John Doe", "Jane Smith"),
  dob          = as.Date(c("1980-01-01", "1975-05-15")),
  mrn          = c("12345", "67890"),
  age5cat      = factor(c("18-64", "18-64")),   # preserved automatically
  diagnosis    = c("Condition A", "Condition B"),
  lab_value    = c(120, 95)
)

result <- suppressMessages(molting(patient_data))
names(result$deidentified)   # hash + retained columns
names(result$lookup)         # hash + removed columns

## ----output-structure---------------------------------------------------------
str(result, max.level = 1)
head(result$lookup)

## ----hash-algos, eval=FALSE---------------------------------------------------
# # SHA-256 (default, recommended)
# result_256 <- molting(patient_data, hash_method = "sha256")
# 
# # MD5 (shorter hash, faster, lower collision resistance)
# result_md5 <- molting(patient_data, hash_method = "md5")
# 
# # Blake3 (fast and cryptographically strong — good for large datasets)
# result_b3 <- molting(patient_data, hash_method = "blake3")

## ----id-cols------------------------------------------------------------------
# Hash only on MRN and DOB — more stable if name variations exist
result_ids <- suppressMessages(
  molting(patient_data, id_cols = c("mrn", "dob"))
)
result_ids$lookup

## ----additional---------------------------------------------------------------
patient_data2 <- patient_data
patient_data2$study_code <- c("SC-001","SC-002")

result2 <- suppressMessages(
  molting(patient_data2, additional_pii_cols = "study_code")
)
names(result2$deidentified)

## ----no-lookup----------------------------------------------------------------
deidentified_only <- suppressMessages(
  molting(patient_data, return_lookup = FALSE)
)
class(deidentified_only)   # a data frame, not a list