From 1ae0544bf571a8fbf73bc29dd8b3c2ff62edb1a4 Mon Sep 17 00:00:00 2001
From: idankars <idankars10@gmail.com>
Date: Sat, 8 Feb 2025 12:21:01 +0200
Subject: [PATCH] Idan Kars answers exercise 10

---
 q1.sh | 21 ++++++++++++++++++++-
 q2.sh | 17 +++++++++++++++++
 2 files changed, 37 insertions(+), 1 deletion(-)
 create mode 100755 q2.sh

diff --git a/q1.sh b/q1.sh
index f7ac848..9d0bdb7 100644
--- a/q1.sh
+++ b/q1.sh
@@ -1 +1,20 @@
-This is q1 answer
+echo "question 1.a"
+awk '{print NR}' aliceinwonderland.txt | tail -n 1
+echo: "3325 rows"
+
+echo "question 1.b"
+awk '{for(i=1;i<=NF;i++) {if($i ~ /^Alice$/) count++}} END {print count}' aliceinwonderland.txt
+echo "212 times, note: in order to find only with spaces before and after, I searched for exactly the word Alice, with no extra characters"
+
+
+echo "question 1.c"
+awk '{for(i=1; i<=NF; i++) {gsub(/[^[:alpha:]]/, "", $i) words[$i]++}} END {for(word in words) {if(words[word] == 1) count++}} END {print count}' aliceinwonderland.txt
+echo "1526 words, note that I removed punctuation, another approach is to look for words containing only alphabetic characters if($i ~ /^[[:alpha:]]+$/)"
+
+echo "question 1.d"
+awk '{for(i=1;i<=NF;i++) if($i ~ /^[[:alpha:]]+$/) print $i}' aliceinwonderland.txt | sort | uniq -c | sort -k 1 -h | tail -n 5 | awk '{print $2}'
+echo "of, a, and, to, the"
+
+echo "question 1.e"
+awk '{for(i=1; i<=NF; i++) {if($i ~ /^[[:alpha:]]+$/) {lengths += length($i);count++;}}} END {print lengths / count}' aliceinwonderland.txt
+echo "3.84393"
diff --git a/q2.sh b/q2.sh
new file mode 100755
index 0000000..bfd053f
--- /dev/null
+++ b/q2.sh
@@ -0,0 +1,17 @@
+echo "question 2.a"
+sed -n '/Holmes\|Sherlock/p' sherlockholmes.txt | wc -l
+echo "463 lines"
+
+echo "question 2.b"
+sed -n '/Holmes\|Sherlock/p' sherlockholmes.txt | grep -Eo 'Sherlock|Holmes' | wc -l
+echo "554 times"
+
+echo "question 2.c"
+sed -E 's/^/Hello: /' sherlockholmes.txt
+
+echo "question 2.d"
+sed -E 's/[A-Z][a-z]+\s[A-Z][a-z]+/Idan/' sherlockholmes.txt
+
+echo "question 2.e"
+sed -E 's/\(/[/g' sherlockholmes.txt | sed -E 's/\)/]/g'
+