Shell 高级主题详解

#!/bin/bash

# 正则表达式示例

echo "=== 基本正则表达式演示 ==="

# 测试文本
text="Hello, my email is user@example.com and my phone is 123-456-7890. Visit https://www.example.com for more info."

echo "原始文本:"
echo "$text"
echo

# 使用grep进行正则匹配
echo "1. 匹配邮箱地址:"
echo "$text" | grep -Eo '[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\.[a-zA-Z]{2,}'

echo -e "\n2. 匹配电话号码:"
echo "$text" | grep -Eo '[0-9]{3}-[0-9]{3}-[0-9]{4}'

echo -e "\n3. 匹配URL:"
echo "$text" | grep -Eo 'https?://[a-zA-Z0-9./?=_-]+'

echo -e "\n4. 匹配单词:"
echo "$text" | grep -Eo '\b[a-zA-Z]{4,}\b' | head -5

echo -e "\n=== 在条件判断中使用正则 ==="

# 在[[ ]]中使用正则匹配
email="user@example.com"

if [[ "$email" =~ ^[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\.[a-zA-Z]{2,}$ ]]; then
echo "有效的邮箱地址: $email"
else
echo "无效的邮箱地址: $email"
fi

# 提取匹配组
text="Date: 2023-11-16, Time: 14:30:25"

if [[ "$text" =~ ([0-9]{4}-[0-9]{2}-[0-9]{2}).*([0-9]{2}:[0-9]{2}:[0-9]{2}) ]]; then
date="${BASH_REMATCH[1]}"
time="${BASH_REMATCH[2]}"
echo "日期: $date"
echo "时间: $time"
fi

echo -e "\n=== 常用正则模式 ==="

# 验证各种格式
validate_pattern() {
local pattern=$1
local test_string=$2
local description=$3

if [[ "$test_string" =~ $pattern ]]; then
    echo "✅ $description: '$test_string'"
else
    echo "❌ $description: '$test_string'"
fi
}

# 测试各种模式
echo "验证用户名（字母开头，3-15字符）:"
validate_pattern '^[a-zA-Z][a-zA-Z0-9_]{2,14}$' "john_doe123" "有效用户名"
validate_pattern '^[a-zA-Z][a-zA-Z0-9_]{2,14}$' "1john" "无效用户名"

echo -e "\n验证密码（至少8字符，包含大小写和数字）:"
validate_pattern '^(?=.*[a-z])(?=.*[A-Z])(?=.*[0-9]).{8,}$' "Password123" "强密码"
validate_pattern '^(?=.*[a-z])(?=.*[A-Z])(?=.*[0-9]).{8,}$' "password" "弱密码"

echo -e "\n验证IP地址:"
validate_pattern '^([0-9]{1,3}\.){3}[0-9]{1,3}$' "192.168.1.1" "有效IP"
validate_pattern '^([0-9]{1,3}\.){3}[0-9]{1,3}$' "256.300.1.1" "无效IP"

echo -e "\n=== 高级正则技巧 ==="

# 使用正则进行复杂文本处理
log_data="2023-11-16 14:30:25 [INFO] User login successful from 192.168.1.100
2023-11-16 14:31:10 [ERROR] Database connection failed
2023-11-16 14:32:45 [WARN] High memory usage detected"

echo "日志分析:"
echo "$log_data" | while read line; do
if [[ "$line" =~ \[(INFO|WARN|ERROR)\].*([0-9]+\.[0-9]+\.[0-9]+\.[0-9]+) ]]; then
    level="${BASH_REMATCH[1]}"
    ip="${BASH_REMATCH[2]:-N/A}"
    echo "级别: $level, IP: $ip"
fi
done

# 使用正则提取和转换
csv_data="name,age,city
John,25,New York
Alice,30,London
Bob,35,Tokyo"

echo -e "\nCSV数据处理:"
echo "$csv_data" | tail -n +2 | while read line; do
if [[ "$line" =~ ^([^,]+),([^,]+),([^,]+)$ ]]; then
    name="${BASH_REMATCH[1]}"
    age="${BASH_REMATCH[2]}"
    city="${BASH_REMATCH[3]}"
    echo "姓名: $name, 年龄: $age, 城市: $city"
fi
done

#!/bin/bash

# sed命令示例

echo "=== sed基本操作 ==="

# 创建测试文件
cat > test.txt << EOF
1. Apple
2. Banana
3. Cherry
4. Date
5. Elderberry
6. Fig
7. Grape
EOF

echo "原始文件内容:"
cat test.txt
echo

echo "1. 替换操作:"
echo "   - 替换第一个匹配:"
sed 's/Banana/Orange/' test.txt

echo -e "\n   - 全局替换:"
sed 's/berry/fruit/g' test.txt

echo -e "\n   - 替换第2行的内容:"
sed '2s/.*/2. Blueberry/' test.txt

echo -e "\n2. 删除操作:"
echo "   - 删除第3行:"
sed '3d' test.txt

echo -e "\n   - 删除包含'berry'的行:"
sed '/berry/d' test.txt

echo -e "\n   - 删除第2-4行:"
sed '2,4d' test.txt

echo -e "\n3. 插入和追加:"
echo "   - 在第3行前插入:"
sed '3i\2.5. Blackberry' test.txt

echo -e "\n   - 在第3行后追加:"
sed '3a\3.5. Blueberry' test.txt

echo -e "\n4. 打印特定行:"
echo "   - 打印第2-4行:"
sed -n '2,4p' test.txt

echo -e "\n   - 打印包含'berry'的行:"
sed -n '/berry/p' test.txt

echo -e "\n=== 高级sed技巧 ==="

# 创建配置文件示例
cat > config.conf << EOF
# Database configuration
db_host=localhost
db_port=3306
db_name=testdb
db_user=admin
db_pass=oldpassword

# Server configuration
server_host=127.0.0.1
server_port=8080
debug_mode=true
EOF

echo "配置文件修改:"
echo "原始配置:"
cat config.conf
echo

echo "1. 修改数据库密码:"
sed -i 's/db_pass=oldpassword/db_pass=newpassword/' config.conf

echo "2. 注释掉debug模式:"
sed -i 's/^debug_mode=true/# debug_mode=true/' config.conf

echo "3. 取消注释（如果存在）:"
sed -i 's/^# db_host/db_host/' config.conf

echo "修改后的配置:"
cat config.conf
echo

echo "=== 使用sed处理日志文件 ==="

# 创建日志文件示例
cat > app.log << EOF
[2023-11-16 14:30:25] INFO: User login successful
[2023-11-16 14:31:10] ERROR: Database connection failed
[2023-11-16 14:32:45] WARN: High memory usage detected
[2023-11-16 14:33:20] INFO: Backup completed
[2023-11-16 14:34:15] ERROR: File not found
EOF

echo "日志分析:"
echo "1. 提取错误日志:"
sed -n '/ERROR/p' app.log

echo -e "\n2. 移除时间戳:"
sed 's/\[.*\] //' app.log

echo -e "\n3. 提取时间信息:"
sed -n 's/.*\[\([0-9:-]\{19\}\)\].*/\1/p' app.log

echo -e "\n4. 给错误日志添加标记:"
sed '/ERROR/s/^/🚨 /' app.log

echo -e "\n=== 复杂的sed脚本 ==="

# 使用多个sed命令
echo "多命令执行:"
sed -e 's/Apple/Red Apple/' \
-e 's/Banana/Yellow Banana/' \
-e '/Cherry/d' \
test.txt

echo -e "\n使用sed脚本文件:"

# 创建sed脚本
cat > process.sed << EOF
# sed脚本示例
s/Apple/Fruit: Apple/
s/Banana/Fruit: Banana/
/berry/ s/$/ (berry fruit)/
1,3s/^/👉 /
EOF

echo "使用sed脚本处理:"
sed -f process.sed test.txt

echo -e "\n=== 就地编辑和备份 ==="

# 创建测试文件
cp test.txt test_backup.txt

echo "就地编辑（创建备份）:"
sed -i.bak 's/^[0-9]\./Item: /' test_backup.txt

echo "修改后的文件:"
cat test_backup.txt

echo -e "\n原始备份文件:"
cat test_backup.txt.bak

# 清理
rm -f test.txt config.conf app.log process.sed test_backup.txt test_backup.txt.bak

#!/bin/bash

# awk命令示例

echo "=== awk基本操作 ==="

# 创建测试数据
cat > data.txt << EOF
Alice 25 Engineer 5000
Bob 30 Manager 8000
Charlie 28 Developer 6000
Diana 35 Director 12000
Eve 22 Intern 3000
Frank 40 Consultant 10000
EOF

echo "原始数据:"
cat data.txt
echo

echo "1. 基本打印:"
echo "   - 打印整行:"
awk '{print $0}' data.txt

echo -e "\n   - 打印特定列:"
awk '{print $1, $4}' data.txt

echo -e "\n   - 打印行号:"
awk '{print NR, $0}' data.txt

echo -e "\n2. 条件过滤:"
echo "   - 年龄大于30岁:"
awk '$2 > 30 {print $1, $2}' data.txt

echo -e "\n   - 薪资高于7000:"
awk '$4 > 7000 {print $1, $4}' data.txt

echo -e "\n   - 职位是Developer:"
awk '$3 == "Developer" {print $0}' data.txt

echo -e "\n3. 模式匹配:"
echo "   - 名字以A或B开头:"
awk '$1 ~ /^[AB]/ {print $0}' data.txt

echo -e "\n   - 包含字母'i':"
awk '/i/ {print $0}' data.txt

echo -e "\n=== 高级awk功能 ==="

echo "4. BEGIN和END块:"
awk 'BEGIN {print "开始处理数据..."; total=0}
 {total += $4; print $1, $4}
 END {print "处理完成"; printf "总薪资: %d\n", total}' data.txt

echo -e "\n5. 内置函数:"
echo "   - 字符串函数:"
awk '{print toupper($1), tolower($3), length($1)}' data.txt

echo -e "\n   - 数学函数:"
awk '{print $1, $4, log($4), sqrt($4)}' data.txt

echo -e "\n6. 数组使用:"
echo "   - 按职位统计人数:"
awk '{count[$3]++} END {for (job in count) print job, count[job]}' data.txt

echo -e "\n   - 按职位统计平均薪资:"
awk '{sum[$3] += $4; count[$3]++}
 END {for (job in sum) printf "%s: %.2f\n", job, sum[job]/count[job]}' data.txt

echo -e "\n=== 处理CSV数据 ==="

# 创建CSV数据
cat > employees.csv << EOF
Name,Age,Department,Salary,JoinDate
John,25,Engineering,5000,2020-01-15
Alice,30,Marketing,6000,2019-03-20
Bob,28,Engineering,5500,2021-06-10
Carol,35,Sales,7000,2018-11-05
David,32,Engineering,6500,2019-09-12
EOF

echo "CSV数据处理:"
echo "原始CSV:"
cat employees.csv
echo

echo "1. 处理表头:"
awk -F, 'NR==1 {print "表头:", $0}' employees.csv

echo -e "\n2. 工程部门员工:"
awk -F, '$3 == "Engineering" {print $1, $4}' employees.csv

echo -e "\n3. 薪资统计:"
awk -F, 'NR>1 {total += $4; count++}
     END {printf "平均薪资: %.2f\n", total/count}' employees.csv

echo -e "\n4. 入职年份统计:"
awk -F, 'NR>1 {year = substr($5, 1, 4); years[year]++}
     END {for (y in years) print y "年入职:", years[y] "人"}' employees.csv

echo -e "\n=== 复杂文本处理 ==="

# 创建日志文件
cat > server.log << EOF
[INFO] 2023-11-16 14:30:25 User alice logged in from 192.168.1.100
[ERROR] 2023-11-16 14:31:10 Database connection timeout
[WARN] 2023-11-16 14:32:45 High memory usage: 85%
[INFO] 2023-11-16 14:33:20 User bob logged out
[ERROR] 2023-11-16 14:34:15 File not found: /var/www/index.html
[INFO] 2023-11-16 14:35:30 Backup completed successfully
EOF

echo "日志分析:"
echo "1. 错误统计:"
awk '/\[ERROR\]/ {count++} END {print "错误数量:", count}' server.log

echo -e "\n2. 提取IP地址:"
awk 'match($0, /[0-9]+\.[0-9]+\.[0-9]+\.[0-9]+/) {print substr($0, RSTART, RLENGTH)}' server.log

echo -e "\n3. 按小时统计日志:"
awk '{split($3, time, ":"); hours[time[1]]++}
 END {for (h in hours) print h "时:", hours[h] "条日志"}' server.log

echo -e "\n4. 自定义输出格式:"
awk 'BEGIN {printf "%-10s %-8s %s\n", "级别", "时间", "消息"}
 /\[/ {level = substr($1, 2, length($1)-2);
       time = $2;
       message = "";
       for(i=3;i<=NF;i++) message = message $i " ";
       printf "%-10s %-8s %s\n", level, time, message}' server.log

echo -e "\n=== awk脚本文件 ==="

# 创建awk脚本
cat > analysis.awk << 'EOF'
# awk脚本示例 - 员工数据分析
BEGIN {
FS = ","
print "=== 员工报告 ==="
total_salary = 0
count = 0
}

NR == 1 {
# 跳过表头
next
}

{
# 处理数据行
name = $1
age = $2
department = $3
salary = $4
join_date = $5

# 累加统计
total_salary += salary
count++
dept_count[department]++
dept_salary[department] += salary

# 输出符合条件的员工
if (salary > 6000) {
    print "高薪员工:", name, salary
}
}

END {
print "\n=== 统计信息 ==="
printf "员工总数: %d\n", count
printf "平均薪资: %.2f\n", total_salary/count

print "\n=== 部门统计 ==="
for (dept in dept_count) {
    avg = dept_salary[dept] / dept_count[dept]
    printf "%-12s: %2d 人, 平均薪资: %8.2f\n", dept, dept_count[dept], avg
}
}
EOF

echo "使用awk脚本分析数据:"
awk -f analysis.awk employees.csv

# 清理
rm -f data.txt employees.csv server.log analysis.awk

#!/bin/bash

# Shell函数示例

echo "=== 基本函数定义 ==="

# 方式1: 使用function关键字
function greet {
echo "Hello, $1!"
}

# 方式2: 不使用function关键字
say_goodbye() {
local name=$1
echo "Goodbye, $name!"
}

# 调用函数
greet "Alice"
say_goodbye "Bob"

echo -e "\n=== 函数参数和返回值 ==="

# 参数处理函数
show_params() {
echo "函数名称: $0"
echo "参数个数: $#"
echo "所有参数: $@"
echo "第一个参数: $1"
echo "第二个参数: $2"

# 使用shift处理参数
while [ $# -gt 0 ]; do
    echo "参数: $1"
    shift
done
}

show_params "apple" "banana" "cherry"

# 返回值函数
calculate_sum() {
local sum=0
for num in "$@"; do
    sum=$((sum + num))
done
return $sum
}

calculate_sum 10 20 30
echo "计算结果: $?"

echo -e "\n=== 局部变量和全局变量 ==="

global_var="我是全局变量"

variable_demo() {
local local_var="我是局部变量"
global_var="我在函数中修改了全局变量"
echo "函数内 - 局部变量: $local_var"
echo "函数内 - 全局变量: $global_var"
}

echo "函数调用前 - 全局变量: $global_var"
variable_demo
echo "函数调用后 - 全局变量: $global_var"
# echo "尝试访问局部变量: $local_var"  # 这会报错

echo -e "\n=== 高级函数特性 ==="

# 函数返回字符串
get_timestamp() {
date '+%Y-%m-%d %H:%M:%S'
}

# 函数返回数组
create_array() {
local arr=("$@")
echo "${arr[@]}"
}

# 使用命令替换获取函数输出
current_time=$(get_timestamp)
echo "当前时间: $current_time"

# 数组返回
my_array=($(create_array "one" "two" "three"))
echo "数组内容: ${my_array[@]}"

echo -e "\n=== 函数库示例 ==="

# 数学函数库
math_functions() {
# 加法
add() {
    echo $(($1 + $2))
}

# 减法
subtract() {
    echo $(($1 - $2))
}

# 乘法
multiply() {
    echo $(($1 * $2))
}

# 除法
divide() {
    if [ $2 -eq 0 ]; then
        echo "错误: 除数不能为0" >&2
        return 1
    fi
    echo $(($1 / $2))
}

# 幂运算
power() {
    local result=1
    local base=$1
    local exponent=$2

    for ((i=0; i&2
    return 1
fi

local result=$((numerator / denominator))
echo $result
return 0
}

# 测试错误处理
if result=$(safe_division 10 2); then
echo "除法成功: $result"
else
echo "除法失败"
fi

if result=$(safe_division 10 0); then
echo "除法成功: $result"
else
echo "除法失败"
fi

echo -e "\n=== 递归函数 ==="

# 阶乘函数（递归）
factorial() {
local n=$1

# 基本情况
if [ $n -le 1 ]; then
    echo 1
    return
fi

# 递归情况
local prev=$(factorial $((n-1)))
echo $((n * prev))
}

echo "递归计算阶乘:"
echo "5! = $(factorial 5)"
echo "10! = $(factorial 10)"

# 斐波那契数列（递归）
fibonacci() {
local n=$1

if [ $n -le 1 ]; then
    echo $n
    return
fi

local a=$(fibonacci $((n-1)))
local b=$(fibonacci $((n-2)))
echo $((a + b))
}

echo -e "\n斐波那契数列:"
for i in {0..10}; do
echo -n "$(fibonacci $i) "
done
echo

echo -e "\n=== 函数作为参数 ==="

# 高阶函数：接受函数作为参数
apply_operation() {
local operation=$1
local a=$2
local b=$3

$operation $a $b
}

# 定义一些操作函数
square() {
echo $(($1 * $1))
}

cube() {
echo $(($1 * $1 * $1))
}

# 使用高阶函数
echo "高阶函数示例:"
echo "5的平方: $(apply_operation square 5)"
echo "3的立方: $(apply_operation cube 3)"

echo -e "\n=== 实用函数库 ==="

# 日志函数
log() {
local level=$1
local message=$2
local timestamp=$(date '+%Y-%m-%d %H:%M:%S')

echo "[$timestamp] [$level] $message" >&2
}

# 文件操作函数
backup_file() {
local file=$1
local backup_dir=${2:-"./backup"}

if [ ! -f "$file" ]; then
    log "ERROR" "文件不存在: $file"
    return 1
fi

mkdir -p "$backup_dir"
local backup_name="${file}.$(date +%Y%m%d_%H%M%S).bak"
cp "$file" "$backup_dir/$backup_name"

if [ $? -eq 0 ]; then
    log "INFO" "文件备份成功: $backup_name"
    return 0
else
    log "ERROR" "文件备份失败: $file"
    return 1
fi
}

# 字符串处理函数
string_utils() {
# 字符串反转
reverse_string() {
    local str=$1
    echo "$str" | rev
}

# 字符串长度
string_length() {
    local str=$1
    echo ${#str}
}

# 转换为大写
to_upper() {
    local str=$1
    echo "$str" | tr '[:lower:]' '[:upper:]'
}

# 转换为小写
to_lower() {
    local str=$1
    echo "$str" | tr '[:upper:]' '[:lower:]'
}
}

# 加载字符串工具
string_utils

# 测试字符串函数
echo "字符串处理:"
echo "反转 'hello': $(reverse_string 'hello')"
echo "'hello' 长度: $(string_length 'hello')"
echo "大写 'hello': $(to_upper 'hello')"
echo "小写 'HELLO': $(to_lower 'HELLO')"

# 测试备份函数
echo "创建测试文件..."
echo "test content" > test_file.txt
backup_file "test_file.txt" "test_backup"

# 清理
rm -f test_file.txt
rm -rf test_backup