Miller

# View CSV data
mlr --csv cat data.csv

# Pretty-print CSV
mlr --csv --ojson cat data.csv | head

# Convert CSV to JSON
mlr --csv --ojson cat data.csv > data.json

# Convert CSV to TOML
mlr --csv --otoml cat data.csv

# Display first N rows
mlr --csv head -n 10 data.csv

# Select specific columns
mlr --csv cut -f name,email,age data.csv

# Filter rows with condition
mlr --csv filter '$age > 30' data.csv

# Multiple conditions
mlr --csv filter '$age > 25 && $status == "active"' data.csv

# Exclude columns
mlr --csv cut -x -f temp_field data.csv

# Filter and select together
mlr --csv filter '$status == "active"' then cut -f name,email data.csv

# Rename columns
mlr --csv rename old_name,new_name data.csv

# Add calculated field
mlr --csv put '$total = $price * $quantity' data.csv

# Format strings
mlr --csv put '$name = toupper($name)' data.csv

# Round numbers
mlr --csv put '$value = round($value, 2)' data.csv

# Conditional assignment
mlr --csv put '$status = $age >= 18 ? "adult" : "minor"' data.csv

# Group by category and count
mlr --csv stats count -g category data.csv

# Sum values by category
mlr --csv stats sum price -g category data.csv

# Multiple aggregations
mlr --csv stats count,sum price,mean age -g department data.csv

# Count distinct values
mlr --csv stats count -a distinct -g product_id data.csv

# Get min/max per group
mlr --csv stats min rating,max rating -g store_id data.csv

# Sort by column
mlr --csv sort -f age data.csv

# Sort numeric (reverse)
mlr --csv sort -nr salary data.csv

# Sort by multiple columns
mlr --csv sort -f department -n age data.csv

# Sort with string case sensitivity
mlr --csv sort -f name data.csv

# CSV to JSON
mlr --csv --ojson cat data.csv

# CSV to TOML
mlr --csv --otoml cat data.csv

# JSON to CSV
mlr --json --ocsv cat data.json

# XML to JSON
mlr --xml --ojson cat data.xml

# Pretty-print JSON
mlr --json --ojson --jvstack cat data.json

# Join two CSV files
mlr --csv join --left --lk id --rk user_id users.csv orders.csv

# Inner join
mlr --csv join --inner --lk id --rk id file1.csv file2.csv

# Use key lookup
mlr --csv step --from users.csv -a getters 'id' then   join --left --lk user_id --rk id orders.csv

# Pivot/reshape data
mlr --csv unsparsify data.csv

# Sample records
mlr --csv sample -k 100 data.csv

# Reverse field order
mlr --csv seqgen -n 10 | mlr --csv shuffle

# Repeat each record
mlr --csv repeat -n 3 data.csv

# Create new field sequences
mlr --csv seqgen -n 1000 | mlr --csv put '$squared = $i ** 2'

# Use put with complex expressions
mlr --csv put '@sum += $amount; @count += 1; @avg = @sum / @count' data.csv

# Define and use variables
mlr --csv put 'begin { @threshold = 100 } $value > @threshold' data.csv

# Use built-in functions
mlr --csv put '$lower = tolower($name); $len = strlen($email)' data.csv

# Loop operations
mlr --csv put 'for (i = 1; i <= 10; i += 1) { @count[i] = 0 }' data.csv

# Process NDJSON (newline-delimited JSON)
mlr --ndjson cat large-file.ndjson

# Filter while streaming
mlr --ndjson filter '$status == "active"' large-file.ndjson

# Streaming aggregation
mlr --csv stats count -g category data.csv

# Process multiple files
mlr --csv --mfn cat *.csv

# Specify record and field separator
mlr --csv --rs '@' --fs ',' cat custom-data.csv

# Compute percentiles
mlr --csv stats p10,p50,p90 -f salary data.csv

# Get cardinality
mlr --csv stats count -a distinct -f product_id data.csv

# Standard deviation and variance
mlr --csv stats stddev,variance -f price data.csv

# Top N values
mlr --csv top -f value -n 10 data.csv

# Filter with regex
mlr --csv filter '$email =~ ".*@gmail\.com"' data.csv

# Match pattern negation
mlr --csv filter '$email !~ ".*@company\.com"' data.csv

# Extract with regex
mlr --csv put '$domain = sub($email, ".*@", "")' data.csv

# Case-insensitive regex
mlr --csv filter '$name =~ "[Jj]ohn"' data.csv