[module]
name = "awk"
description = "Pattern scanning and text processing language"
version = 1
[intro]
text = """
## What is awk?
`awk` is a powerful text-processing language. It reads input line by line, splits each line into fields, and lets you apply actions based on patterns.
## Basic Syntax
```
awk 'pattern { action }' file
```
## Key Concepts
- **Fields:** `$1`, `$2`, ... `$NF` (last field). `$0` is the whole line.
- **FS:** Field separator (default: whitespace). Set with `-F` or `FS=`.
- **NR:** Current record (line) number.
- **NF:** Number of fields on the current line.
- **BEGIN/END:** Special blocks that run before/after processing.
## Common Patterns
`awk '{ print $1 }' file` — print first field of each line
`awk -F: '{ print $1 }' /etc/passwd` — use `:` as delimiter
`awk 'NR==3' file` — print only line 3
`awk '$2 > 100' file` — print lines where field 2 > 100
`awk 'BEGIN { sum=0 } { sum+=$1 } END { print sum }' file` — sum a column
"""
[[examples]]
title = "Print a specific field"
description = "Extract just the first column from space-separated data"
command = "awk '{ print $1 }' data.txt"
output = "alice\nbob\ncharlie\n"
[[examples]]
title = "Custom delimiter"
description = "Use colon as field separator to read /etc/passwd-style files"
command = "awk -F: '{ print $1, $3 }' users.txt"
output = "root 0\nalice 1001\nbob 1002\n"
[[examples]]
title = "Conditional filtering"
description = "Print lines where the second field (score) is greater than 80"
command = "awk '$2 > 80 { print $1, $2 }' scores.txt"
output = "alice 95\ncharlie 87\n"
[[examples]]
title = "Sum a column"
description = "Compute the total of the second column"
command = "awk 'BEGIN { sum=0 } { sum+=$2 } END { print sum }' scores.txt"
output = "265\n"
[[exercises]]
id = "awk.1"
difficulty = "beginner"
question = """The file `people.txt` has lines with name and age separated by spaces.
Print only the names (first field)."""
expected_output = "Alice\nBob\nCharlie\nDiana\n"
hints = [
"awk prints fields with $1, $2, etc.",
"Try: awk '{ print $1 }' people.txt",
]
solution = "awk '{ print $1 }' people.txt"
match_mode = "exact"
[[exercises.fixtures]]
filename = "people.txt"
content = "Alice 30\nBob 25\nCharlie 35\nDiana 28\n"
[[exercises]]
id = "awk.2"
difficulty = "beginner"
question = """The file `scores.txt` has student names and scores.
Print only lines where the score (second field) is greater than 80."""
expected_output = "Alice 95\nCharlie 87\n"
hints = [
"Use a condition before the action block",
"Try: awk '$2 > 80' scores.txt",
]
solution = "awk '$2 > 80' scores.txt"
match_mode = "exact"
[[exercises.fixtures]]
filename = "scores.txt"
content = "Alice 95\nBob 72\nCharlie 87\nDiana 61\n"
[[exercises]]
id = "awk.3"
difficulty = "beginner"
question = """The file `csv.txt` uses commas as delimiters.
Print the second field (city) from each line."""
expected_output = "New York\nLos Angeles\nChicago\n"
hints = [
"Use -F to set the field separator",
"Try: awk -F, '{ print $2 }' csv.txt",
]
solution = "awk -F, '{ print $2 }' csv.txt"
match_mode = "exact"
[[exercises.fixtures]]
filename = "csv.txt"
content = "Alice,New York,Engineer\nBob,Los Angeles,Designer\nCharlie,Chicago,Manager\n"
[[exercises]]
id = "awk.4"
difficulty = "beginner"
question = """The file `numbers.txt` has one number per line.
Use awk to compute and print the sum of all numbers."""
expected_output = "150\n"
hints = [
"Accumulate in a variable, print in END block",
"Try: awk '{ sum += $1 } END { print sum }' numbers.txt",
]
solution = "awk '{ sum += $1 } END { print sum }' numbers.txt"
match_mode = "exact"
[[exercises.fixtures]]
filename = "numbers.txt"
content = "10\n20\n30\n40\n50\n"
[[exercises]]
id = "awk.5"
difficulty = "intermediate"
question = """The file `data.txt` has lines with name and score.
Print the name and score for lines where the score is between 50 and 80 (inclusive)."""
expected_output = "Bob 72\nDiana 61\nEve 55\n"
hints = [
"Use && to combine conditions",
"Try: awk '$2 >= 50 && $2 <= 80' data.txt",
]
solution = "awk '$2 >= 50 && $2 <= 80' data.txt"
match_mode = "exact"
[[exercises.fixtures]]
filename = "data.txt"
content = "Alice 95\nBob 72\nCharlie 87\nDiana 61\nEve 55\nFrank 42\n"
[[exercises]]
id = "awk.6"
difficulty = "intermediate"
question = """The file `log.txt` has lines prefixed with line numbers using NR.
Print each line prefixed with its line number and a colon (e.g. '1: first line')."""
expected_output = "1: apple\n2: banana\n3: cherry\n"
hints = [
"NR holds the current line number",
"Try: awk '{ print NR\": \"$0 }' log.txt",
]
solution = "awk '{ print NR\": \"$0 }' log.txt"
match_mode = "exact"
[[exercises.fixtures]]
filename = "log.txt"
content = "apple\nbanana\ncherry\n"
[[exercises]]
id = "awk.7"
difficulty = "intermediate"
question = """The file `employees.txt` has department, name, and salary fields.
Print the average salary of all employees."""
expected_output = "75000\n"
hints = [
"Sum the salary field ($3) and divide by NR at the END",
"Try: awk '{ sum+=$3 } END { print sum/NR }' employees.txt",
]
solution = "awk '{ sum+=$3 } END { print sum/NR }' employees.txt"
match_mode = "exact"
[[exercises.fixtures]]
filename = "employees.txt"
content = "Engineering Alice 80000\nMarketing Bob 60000\nEngineering Charlie 90000\nMarketing Diana 70000\n"
[[exercises]]
id = "awk.8"
difficulty = "intermediate"
question = """The file `data.csv` uses commas. Print each line reformatted as 'NAME is AGE years old'."""
expected_output = "Alice is 30 years old\nBob is 25 years old\nCharlie is 35 years old\n"
hints = [
"Use -F, and string concatenation in print",
"Try: awk -F, '{ print $1 \" is \" $2 \" years old\" }' data.csv",
]
solution = "awk -F, '{ print $1 \" is \" $2 \" years old\" }' data.csv"
match_mode = "exact"
[[exercises.fixtures]]
filename = "data.csv"
content = "Alice,30\nBob,25\nCharlie,35\n"
[[exercises]]
id = "awk.9"
difficulty = "advanced"
question = """The file `sales.txt` has product and amount per line.
Print a summary: each unique product and its total sales amount."""
expected_output = "apple 150\nbanana 90\norange 60\n"
hints = [
"Use an associative array to accumulate totals per product",
"In END, iterate over the array with for (key in arr)",
"Try: awk '{ total[$1]+=$2 } END { for (p in total) print p, total[p] }' sales.txt | sort",
]
solution = "awk '{ total[$1]+=$2 } END { for (p in total) print p, total[p] }' sales.txt | sort"
match_mode = "sorted"
[[exercises.fixtures]]
filename = "sales.txt"
content = "apple 50\nbanana 30\napple 60\norange 60\nbanana 60\napple 40\n"
[[exercises]]
id = "awk.10"
difficulty = "advanced"
question = """The file `records.txt` has fields separated by '|'.
Print lines where the third field starts with 'A', reformatted as 'FIELD1 -> FIELD3'."""
expected_output = "001 -> Alice\n003 -> Anna\n"
hints = [
"Use -F'|' as delimiter and ~ for regex match",
"Try: awk -F'|' '$3 ~ /^A/ { print $1 \" -> \" $3 }' records.txt",
]
solution = "awk -F'|' '$3 ~ /^A/ { print $1 \" -> \" $3 }' records.txt"
match_mode = "exact"
[[exercises.fixtures]]
filename = "records.txt"
content = "001|Engineering|Alice\n002|Marketing|Bob\n003|Sales|Anna\n004|Engineering|Charlie\n"