1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
|
#!/usr/bin/env python3
import json
import random
import string
import sys
import os
from datetime import datetime
def random_string(length: int) -> str:
return "".join(random.choices(string.ascii_letters + string.digits + " ", k=length))
def random_email() -> str:
username = "".join(random.choices(string.ascii_lowercase, k=random.randint(5, 12)))
domain = "".join(random.choices(string.ascii_lowercase, k=random.randint(4, 8)))
tld = random.choice(["com", "org", "net", "edu", "gov"])
return f"{username}@{domain}.{tld}"
def random_phone() -> str:
return f"+1-{random.randint(100, 999)}-{random.randint(100, 999)}-{random.randint(1000, 9999)}"
def generate_user():
return {
"id": random.randint(1, 1000000),
"username": random_string(random.randint(6, 15)),
"email": random_email(),
"first_name": random_string(random.randint(4, 12)),
"last_name": random_string(random.randint(4, 15)),
"age": random.randint(18, 80),
"phone": random_phone(),
"is_active": random.choice([True, False]),
"balance": round(random.uniform(0, 10000), 2),
"tags": [
random_string(random.randint(3, 8)) for _ in range(random.randint(1, 5))
],
"metadata": {
"last_login": f"2024-{random.randint(1, 12):02d}-{random.randint(1, 28):02d}T{random.randint(0, 23):02d}:{random.randint(0, 59):02d}:{random.randint(0, 59):02d}Z",
"login_count": random.randint(0, 500),
"preferences": {
"theme": random.choice(["dark", "light", "auto"]),
"notifications": random.choice([True, False]),
"language": random.choice(["en", "es", "fr", "de", "ja"]),
},
},
}
def generate_product():
return {
"id": f"prod_{random.randint(1000, 99999)}",
"name": random_string(random.randint(10, 30)),
"description": random_string(random.randint(50, 200)),
"price": round(random.uniform(1, 1000), 2),
"category": random.choice(
["electronics", "clothing", "books", "home", "sports", "toys"]
),
"in_stock": random.randint(0, 100),
"rating": round(random.uniform(1, 5), 1),
"reviews": random.randint(0, 1000),
"specifications": {
"weight": f"{random.uniform(0.1, 50):.2f}kg",
"dimensions": f"{random.randint(1, 100)}x{random.randint(1, 100)}x{random.randint(1, 100)}cm",
"color": random.choice(
["red", "blue", "green", "black", "white", "yellow", "purple"]
),
},
}
def generate_order():
return {
"order_id": f"order_{random.randint(10000, 999999)}",
"user_id": random.randint(1, 1000000),
"items": [
{
"product_id": f"prod_{random.randint(1000, 99999)}",
"quantity": random.randint(1, 5),
"price": round(random.uniform(10, 500), 2),
}
for _ in range(random.randint(1, 8))
],
"total": round(random.uniform(20, 2000), 2),
"status": random.choice(
["pending", "processing", "shipped", "delivered", "cancelled"]
),
"created_at": f"2024-{random.randint(1, 12):02d}-{random.randint(1, 28):02d}T{random.randint(0, 23):02d}:{random.randint(0, 59):02d}:{random.randint(0, 59):02d}Z",
"shipping_address": {
"street": f"{random.randint(1, 9999)} {random_string(random.randint(5, 15))} St",
"city": random_string(random.randint(6, 12)),
"state": random_string(2).upper(),
"zip_code": f"{random.randint(10000, 99999)}",
"country": "US",
},
}
def generate_large_json(target_size_mb: int, output_file: str):
target_size_bytes = target_size_mb * 1024 * 1024
data = {
"metadata": {
"generated_at": datetime.now().isoformat(),
"target_size_mb": target_size_mb,
"generator_version": "1.0",
},
"users": [],
"products": [],
"orders": [],
"analytics": {"page_views": [], "server_metrics": []},
}
print(f"Generating JSON file targeting {target_size_mb}MB...")
# Keep track of approximate size
current_size = 0
batch_size = 100 # Generate in batches to avoid memory issues
while current_size < target_size_bytes:
# Add users
for _ in range(batch_size):
data["users"].append(generate_user())
# Add products
for _ in range(batch_size // 2):
data["products"].append(generate_product())
# Add orders
for _ in range(batch_size // 3):
data["orders"].append(generate_order())
# Add some analytics data
for _ in range(batch_size):
data["analytics"]["page_views"].append(
{
"timestamp": f"2024-{random.randint(1, 12):02d}-{random.randint(1, 28):02d}T{random.randint(0, 23):02d}:{random.randint(0, 59):02d}:{random.randint(0, 59):02d}Z",
"page": f"/{random_string(random.randint(5, 15))}",
"user_id": random.randint(1, 1000000),
"duration": random.randint(1, 300),
}
)
for _ in range(batch_size // 10):
data["analytics"]["server_metrics"].append(
{
"timestamp": f"2024-{random.randint(1, 12):02d}-{random.randint(1, 28):02d}T{random.randint(0, 23):02d}:{random.randint(0, 59):02d}:{random.randint(0, 59):02d}Z",
"cpu_usage": round(random.uniform(0, 100), 2),
"memory_usage": round(random.uniform(0, 100), 2),
"disk_io": random.randint(0, 1000),
"network_io": random.randint(0, 10000),
}
)
# Estimate current size (rough approximation)
current_size = (
len(data["users"]) * 400 # Rough estimate per user
+ len(data["products"]) * 300
+ len(data["orders"]) * 500
+ len(data["analytics"]["page_views"]) * 150
+ len(data["analytics"]["server_metrics"]) * 200
)
if (
current_size % (10 * 1024 * 1024) < batch_size * 400
): # Print progress every ~10MB
print(f"Generated approximately {current_size / (1024 * 1024):.1f}MB...")
print(f"Writing to {output_file}...")
with open(output_file, "w") as f:
json.dump(data, f, separators=(",", ":")) # Compact format
# Get actual file size
actual_size = os.path.getsize(output_file)
actual_size_mb = actual_size / (1024 * 1024)
print(f"✓ Generated {output_file}")
print(f" Target size: {target_size_mb}MB")
print(f" Actual size: {actual_size_mb:.1f}MB ({actual_size:,} bytes)")
print(f" Users: {len(data['users']):,}")
print(f" Products: {len(data['products']):,}")
print(f" Orders: {len(data['orders']):,}")
print(f" Page views: {len(data['analytics']['page_views']):,}")
print(f" Server metrics: {len(data['analytics']['server_metrics']):,}")
def generate_descriptive(target_size_mb: int, output_file: str):
target_size_bytes = target_size_mb * 1024 * 1024
data = []
current_size = 0
batch_size = 100
print(f"Generating descriptive JSON array targeting {target_size_mb}MB...")
while current_size < target_size_bytes:
batch = [
{
"name": random_string(40),
"description": random_string(400),
}
for _ in range(batch_size)
]
data.extend(batch)
# Estimate current size (approximate: 40+400 chars per object + overhead)
current_size = len(data) * (40 + 400 + 30)
if current_size % (10 * 1024 * 1024) < batch_size * (40 + 400):
print(f"Generated approximately {current_size / (1024 * 1024):.1f}MB...")
print(f"Writing to {output_file}...")
with open(output_file, "w") as f:
json.dump(data, f, separators=(",", ":"))
actual_size = os.path.getsize(output_file)
actual_size_mb = actual_size / (1024 * 1024)
print(f"✓ Generated {output_file}")
print(f" Target size: {target_size_mb}MB")
print(f" Actual size: {actual_size_mb:.1f}MB ({actual_size:,} bytes)")
print(f" Objects: {len(data):,}")
def main():
assert len(sys.argv) == 2
try:
target_size = int(sys.argv[1])
except ValueError:
print("Usage: python3 generate_json.py [size_in_mb]")
sys.exit(1)
output_file = f"descriptive-{target_size}MB.json"
generate_descriptive(target_size, output_file)
if __name__ == "__main__":
main()
|
