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

## ----essential-functions, results='asis', echo=FALSE, message=FALSE, warning=FALSE----
library(engager)

essential_functions <- c(
  "basic_transcript_analysis",
  "quick_analysis",
  "batch_basic_analysis",
  "load_zoom_transcript",
  "process_zoom_transcript",
  "consolidate_transcript",
  "summarize_transcript_metrics",
  "summarize_transcript_files",
  "analyze_transcripts",
  "plot_users",
  "write_metrics",
  "load_roster",
  "detect_unmatched_names",
  "match_names_workflow",
  "write_unresolved",
  "ensure_privacy",
  "privacy_audit",
  "anonymize_educational_data",
  "validate_privacy_compliance",
  "review_privacy_risks",
  "generate_privacy_review_report"
)

stopifnot(all(essential_functions %in% getNamespaceExports("engager")))

# Emit a markdown list with autolinkable inline code items
cat("Supported workflow functions (", length(essential_functions), "):\n\n")
cat(paste0("- `", essential_functions, "()`"), sep = "\n")

## ----load-transcript----------------------------------------------------------
# Load a sample transcript
transcript_file <- system.file("extdata/test_transcripts/intro_statistics_week1.vtt",
  package = "engager"
)

# Load the transcript
transcript <- load_zoom_transcript(transcript_file)
cat("Transcript loaded with", nrow(transcript), "comments\n")

## ----process-transcript-------------------------------------------------------
# Process transcript with privacy defaults
processed <- process_zoom_transcript(
  transcript_df = transcript,
  add_dead_air = TRUE,
  consolidate_comments = TRUE
)

metrics <- summarize_transcript_metrics(
  transcript_df = processed,
  names_exclude = c("dead_air")
)

head(metrics)

## ----plot-and-export----------------------------------------------------------
engagement_plot <- plot_users(
  metrics,
  metric = "n",
  facet_by = "none",
  mask_by = "name"
)
print(engagement_plot)

output_file <- tempfile(fileext = ".csv")
write_metrics(
  metrics,
  what = "engagement",
  path = output_file,
  comments_policy = "omit"
)
stopifnot(file.exists(output_file))
unlink(output_file)

## ----privacy-compliance-------------------------------------------------------
# Check privacy risk with synthetic data
synthetic_data <- data.frame(
  name = c("Student A", "Student B", "Instructor"),
  message = c("Hello", "Good morning", "Welcome to class"),
  timestamp = c("00:01:00", "00:02:00", "00:00:30")
)

# Privacy review helpers flag recognized identifier-like columns. They do not
# prove that a data set or free-text field contains no identifying information.
privacy_review <- review_privacy_risks(synthetic_data, audit_log = FALSE)
privacy_review$pii_detected
privacy_review$recommendations