Pattern Detection

# Find functions with 50+ lines
grep -n "function\|def\|func " **/*.{js,ts,py,go} | \
  while read line; do
    file=$(echo $line | cut -d: -f1)
    linenum=$(echo $line | cut -d: -f2)
    # Function length calculation logic
  done

# Search for similar code blocks
grep -rn "if.*==.*null" --include="*.ts" .
grep -rn "try\s*{" --include="*.java" . | wc -l

# Search for hard-coded numbers
grep -rn "[^a-zA-Z][0-9]{2,}[^a-zA-Z]" --include="*.{js,ts}" .

# SQL query built via string concatenation
grep -rn "query.*+.*\$\|execute.*%s\|query.*f\"" --include="*.py" .
grep -rn "SELECT.*\+.*\|\|" --include="*.{js,ts}" .

# Password, API key patterns
grep -riE "(password|secret|api_key|apikey)\s*=\s*['\"][^'\"]+['\"]" --include="*.{js,ts,py,java}" .

# AWS key patterns
grep -rE "AKIA[0-9A-Z]{16}" .

# eval, exec usage
grep -rn "eval\(.*\)\|exec\(.*\)" --include="*.{py,js}" .

# innerHTML usage
grep -rn "innerHTML\s*=" --include="*.{js,ts}" .

# Candidates for unused imports
grep -rn "^import\|^from.*import" --include="*.py" . | \
  awk -F: '{print $3}' | sort | uniq -c | sort -rn

# Find unfinished code
grep -rn "TODO\|FIXME\|HACK\|XXX" --include="*.{js,ts,py}" .

# Empty catch blocks
grep -rn "catch.*{[\s]*}" --include="*.{js,ts,java}" .

# Ignored errors
grep -rn "except:\s*pass" --include="*.py" .

import re

patterns = {
    'email': r'[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\.[a-zA-Z]{2,}',
    'phone': r'\d{3}[-.\s]?\d{4}[-.\s]?\d{4}',
    'ip_address': r'\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}',
    'credit_card': r'\d{4}[-\s]?\d{4}[-\s]?\d{4}[-\s]?\d{4}',
    'ssn': r'\d{3}-\d{2}-\d{4}',
}

def detect_sensitive_data(text):
    found = {}
    for name, pattern in patterns.items():
        matches = re.findall(pattern, text)
        if matches:
            found[name] = len(matches)
    return found

import numpy as np
from scipy import stats

def detect_anomalies_zscore(data, threshold=3):
    """Z-score-based outlier detection"""
    z_scores = np.abs(stats.zscore(data))
    return np.where(z_scores > threshold)[0]

def detect_anomalies_iqr(data, k=1.5):
    """IQR-based outlier detection"""
    q1, q3 = np.percentile(data, [25, 75])
    iqr = q3 - q1
    lower = q1 - k * iqr
    upper = q3 + k * iqr
    return np.where((data < lower) | (data > upper))[0]

import pandas as pd

def analyze_trend(df, date_col, value_col):
    """Time-series trend analysis"""
    df[date_col] = pd.to_datetime(df[date_col])
    df = df.sort_values(date_col)

    # Moving averages
    df['ma_7'] = df[value_col].rolling(window=7).mean()
    df['ma_30'] = df[value_col].rolling(window=30).mean()

    # Growth rate
    df['growth'] = df[value_col].pct_change() * 100

    # Trend direction
    recent_trend = df['ma_7'].iloc[-1] > df['ma_30'].iloc[-1]

    return {
        'trend_direction': 'up' if recent_trend else 'down',
        'avg_growth': df['growth'].mean(),
        'volatility': df[value_col].std()
    }

# Pattern Detection Report

## Summary
- Files scanned: XXX
- Patterns detected: XX
- High severity: X
- Medium severity: X
- Low severity: X

## Detected patterns

### Security vulnerabilities (HIGH)
| File | Line | Pattern | Description |
|------|------|------|------|
| file.js | 42 | hardcoded-secret | Hard-coded API key |

### Code smells (MEDIUM)
| File | Line | Pattern | Description |
|------|------|------|------|
| util.py | 100 | long-function | Function length: 150 lines |

## Recommended actions
1. [Action 1]
2. [Action 2]