08 · Data Formats#

>>> "नमस्ते 🙏".encode("utf-8")
b'\xe0\xa4\xa8\xe0\xa4\xae\xe0\xa4\xb8\xe0\xa5\x8d\xe0\xa4\xa4\xe0\xa5\x87 \xf0\x9f\x99\x8f'

>>> len("नमस्ते 🙏")              # 7 code points
7
>>> len("नमस्ते 🙏".encode("utf-8"))  # 21 bytes
21

# When reading files:
open("file.txt", encoding="utf-8")   # be explicit on Windows

# In HTTP:
Content-Type: application/json; charset=utf-8

{
  "name": "Alice",
  "age": 30,
  "is_admin": true,
  "roles": ["editor", "reviewer"],
  "address": {
    "city": "Chennai",
    "pin": "600113"
  },
  "deleted_at": null
}

import json

# Serialize
data = {"name": "Alice", "scores": [1, 2, 3]}
s = json.dumps(data, indent=2, ensure_ascii=False)
# ensure_ascii=False keeps Unicode characters readable

# Parse
data = json.loads(s)

# Files
json.dump(data, open("out.json", "w"))
data = json.load(open("out.json"))

# Pretty-print
cat data.json | jq .

# Validate
jq empty < data.json      # exits non-zero on bad JSON

# Edit a field
jq '.name = "Bob"' data.json > new.json

name: Deploy
on:
  push:
    branches: [main]
  pull_request:

jobs:
  test:
    runs-on: ubuntu-latest
    env:
      API_KEY: ${{ secrets.API_KEY }}
    steps:
      - uses: actions/checkout@v4
      - name: Run tests
        run: |
          uv sync
          uv run pytest

# All three are equivalent strings:
- foo
- "foo"
- 'foo'

# But these are DIFFERENT:
- true          # boolean true
- "true"        # string "true"
- yes           # boolean true (!!!)
- on            # boolean true (!!!)

# Anchors and aliases let you reuse values
defaults: &defaults
  timeout: 30
  retries: 3

prod:
  <<: *defaults
  url: https://prod

staging:
  <<: *defaults
  url: https://staging

# Library: PyYAML (install: `uv add pyyaml`)
import yaml

data = yaml.safe_load(open("config.yml"))   # ← always safe_load, not load
yaml.safe_dump(data, open("out.yml", "w"), sort_keys=False)

[project]
name = "my-package"
version = "0.1.0"
description = "A sample package."
readme = "README.md"
requires-python = ">=3.11"
license = "MIT"
dependencies = [
    "requests>=2.31",
    "pydantic>=2",
]

[project.optional-dependencies]
dev = ["pytest", "ruff"]

[project.scripts]
my-cli = "my_package.cli:main"

[tool.ruff]
line-length = 100

# Strings
name = "Alice"
multiline = """
First line.
Second line.
"""

# Numbers
age = 30
pi = 3.14
hex = 0xdeadbeef

# Booleans
debug = true

# Arrays
tags = ["python", "rust", "fast"]

# Tables (= maps / objects / dicts)
[database]
host = "localhost"
port = 5432

# Array of tables
[[users]]
name = "Alice"
[[users]]
name = "Bob"

# Dates
start = 2026-05-10
birthday = 1993-06-15T08:30:00Z

# Python 3.11+ has built-in tomllib (read only):
import tomllib
with open("pyproject.toml", "rb") as f:     # binary mode required!
    data = tomllib.load(f)

# To write, use `tomli-w` (uv add tomli-w):
import tomli_w
tomli_w.dumps(data)

# Heading 1
## Heading 2

**Bold** and *italic* and `inline code`.

- bullet list
- item two

1. numbered list
2. item two

[Link text](https://example.com)
![Alt text](./image.png)

> A blockquote.

| Column A | Column B |
|----------|----------|
| cell 1   | cell 2   |

\`\`\`python
# Code block with syntax highlighting
print("hello")
\`\`\`

import base64

encoded = base64.b64encode(b"hello").decode("ascii")
# 'aGVsbG8='

decoded = base64.b64decode(encoded)
# b'hello'

echo -n "hello" | base64              # aGVsbG8=
echo -n "aGVsbG8=" | base64 -d         # hello

# Binary file → base64 text
base64 < photo.png > photo.b64
base64 -d < photo.b64 > copy.png

# uv add msgpack
import msgpack
data = {"name": "Alice", "scores": [1, 2, 3]}

packed = msgpack.packb(data)     # bytes, ~3x smaller than JSON
msgpack.unpackb(packed)           # round-trip

{
  "project": "tds-2026",
  "semester": 2,
  "instructors": ["Anand", "Priyanshu"],
  "grading": {"ga": 0.4, "projects": 0.4, "roe": 0.2}
}