chore: Issue closure 125 cleanup

This commit is contained in:
2025-10-05 12:49:28 +02:00
parent 20e7f0f5bd
commit bce680e6cb
26 changed files with 2362 additions and 388 deletions

View File

@@ -0,0 +1,210 @@
"""
Test suite for file utility functions.
"""
import os
import tempfile
from pathlib import Path
import pytest
from markitect_utils.file_utils import (
safe_filename,
ensure_extension,
get_file_size,
is_text_file,
normalize_path,
)
class TestSafeFilename:
"""Test cases for the safe_filename function."""
def test_basic_sanitization(self):
"""Test basic filename sanitization."""
assert safe_filename("normal_file.txt") == "normal_file.txt"
assert safe_filename("file with spaces.txt") == "file with spaces.txt"
def test_unsafe_characters(self):
"""Test removal of unsafe characters."""
assert safe_filename("file<>name.txt") == "file__name.txt"
assert safe_filename('file"name.txt') == "file_name.txt"
assert safe_filename("file/path\\name.txt") == "file_path_name.txt"
assert safe_filename("file|name.txt") == "file_name.txt"
def test_custom_replacement(self):
"""Test custom replacement character."""
assert safe_filename("file<>name.txt", "-") == "file--name.txt"
assert safe_filename("file/path\\name.txt", "") == "filepathname.txt"
def test_reserved_names(self):
"""Test handling of Windows reserved names."""
assert safe_filename("CON") == "file_CON"
assert safe_filename("PRN.txt") == "file_PRN.txt"
assert safe_filename("COM1") == "file_COM1"
assert safe_filename("con") == "file_con" # case insensitive
def test_edge_cases(self):
"""Test edge cases."""
assert safe_filename("") == "" # Empty input returns empty
assert safe_filename(" ") == "file_" # Whitespace only gets prefix
assert safe_filename("...") == "file_" # Dots only gets prefix
assert safe_filename(".hidden") == "hidden" # Leading dot gets stripped
class TestEnsureExtension:
"""Test cases for the ensure_extension function."""
def test_add_extension(self):
"""Test adding extension to filename."""
assert ensure_extension("document", ".md") == "document.md"
assert ensure_extension("file", "txt") == "file.txt"
def test_existing_extension(self):
"""Test when extension already exists."""
assert ensure_extension("document.md", ".md") == "document.md"
assert ensure_extension("file.txt", "txt") == "file.txt"
def test_different_extension(self):
"""Test adding extension when different one exists."""
assert ensure_extension("document.txt", ".md") == "document.txt.md"
assert ensure_extension("file.doc", "pdf") == "file.doc.pdf"
def test_edge_cases(self):
"""Test edge cases."""
assert ensure_extension("", ".md") == ""
assert ensure_extension("file", "") == "file"
assert ensure_extension("file.md", "") == "file.md"
class TestGetFileSize:
"""Test cases for the get_file_size function."""
def test_existing_file(self):
"""Test getting size of existing file."""
with tempfile.NamedTemporaryFile(mode='w', delete=False) as f:
f.write("Hello, World!")
temp_path = f.name
try:
size = get_file_size(temp_path)
assert size is not None
assert size > 0
finally:
os.unlink(temp_path)
def test_nonexistent_file(self):
"""Test getting size of non-existent file."""
assert get_file_size("/path/that/does/not/exist") is None
def test_empty_file(self):
"""Test getting size of empty file."""
with tempfile.NamedTemporaryFile(delete=False) as f:
temp_path = f.name
try:
size = get_file_size(temp_path)
assert size == 0
finally:
os.unlink(temp_path)
def test_path_object(self):
"""Test with Path object."""
with tempfile.NamedTemporaryFile(mode='w', delete=False) as f:
f.write("test content")
temp_path = Path(f.name)
try:
size = get_file_size(temp_path)
assert size is not None
assert size > 0
finally:
os.unlink(temp_path)
class TestIsTextFile:
"""Test cases for the is_text_file function."""
def test_text_file(self):
"""Test with actual text file."""
with tempfile.NamedTemporaryFile(mode='w', delete=False, suffix='.txt') as f:
f.write("This is a text file with some content.")
temp_path = f.name
try:
assert is_text_file(temp_path) is True
finally:
os.unlink(temp_path)
def test_binary_file(self):
"""Test with binary file."""
with tempfile.NamedTemporaryFile(mode='wb', delete=False, suffix='.bin') as f:
f.write(b'\x00\x01\x02\x03\x04\x05')
temp_path = f.name
try:
assert is_text_file(temp_path) is False
finally:
os.unlink(temp_path)
def test_empty_file(self):
"""Test with empty file."""
with tempfile.NamedTemporaryFile(delete=False) as f:
temp_path = f.name
try:
assert is_text_file(temp_path) is True # Empty files are considered text
finally:
os.unlink(temp_path)
def test_unicode_file(self):
"""Test with Unicode text file."""
with tempfile.NamedTemporaryFile(mode='w', delete=False, encoding='utf-8') as f:
f.write("Hello 世界! This is UTF-8 text.")
temp_path = f.name
try:
assert is_text_file(temp_path) is True
finally:
os.unlink(temp_path)
def test_nonexistent_file(self):
"""Test with non-existent file."""
assert is_text_file("/path/that/does/not/exist") is False
class TestNormalizePath:
"""Test cases for the normalize_path function."""
def test_relative_path(self):
"""Test normalizing relative paths."""
# Note: These tests are environment-dependent
result = normalize_path("./test")
assert os.path.isabs(result)
assert result.endswith("test")
def test_path_with_dots(self):
"""Test path with dot components."""
result = normalize_path("./dir/../file.txt")
assert os.path.isabs(result)
assert result.endswith("file.txt")
def test_already_absolute(self):
"""Test already absolute path."""
abs_path = "/tmp/test/file.txt"
result = normalize_path(abs_path)
assert result == abs_path
def test_path_object(self):
"""Test with Path object."""
path_obj = Path("./test/file.txt")
result = normalize_path(path_obj)
assert os.path.isabs(result)
assert isinstance(result, str)
def test_edge_cases(self):
"""Test edge cases."""
assert normalize_path("") == ""
# Current directory should normalize to absolute path
result = normalize_path(".")
assert os.path.isabs(result)

View File

@@ -0,0 +1,175 @@
"""
Integration tests for markitect-utils capability.
Tests the overall functionality and integration of the utility modules.
"""
import tempfile
import os
from pathlib import Path
import pytest
from markitect_utils import (
slugify, safe_filename, is_valid_email, validate_required_fields,
truncate, normalize_path
)
class TestUtilityIntegration:
"""Test integration between different utility functions."""
def test_filename_processing_workflow(self):
"""Test a complete filename processing workflow."""
# Start with user input
user_title = "My Great Article: A Case Study!"
user_email = "author@example.com"
# Validate email
assert is_valid_email(user_email) is True
# Create a slug for URL
slug = slugify(user_title)
assert slug == "my-great-article-a-case-study"
# Create a safe filename
filename = safe_filename(f"{slug}.md")
assert filename == "my-great-article-a-case-study.md"
# Truncate if too long
if len(filename) > 30:
filename = truncate(filename, 30, "….md")
assert len(filename) <= 30
assert filename.endswith(".md") or filename.endswith("….md")
def test_content_validation_workflow(self):
"""Test a content validation workflow."""
# Simulate form data
form_data = {
"title": "My Article",
"content": "This is the content of my article.",
"author_email": "author@example.com",
"category": "", # Empty field
"tags": "python,utils,testing"
}
required_fields = ["title", "content", "author_email", "category"]
# Validate required fields
validation_result = validate_required_fields(form_data, required_fields)
assert validation_result["missing"] == []
assert validation_result["empty"] == ["category"]
# Validate email format
if form_data.get("author_email"):
assert is_valid_email(form_data["author_email"]) is True
# Process tags
if form_data.get("tags"):
tag_list = [slugify(tag.strip()) for tag in form_data["tags"].split(",")]
assert tag_list == ["python", "utils", "testing"]
def test_file_operations_workflow(self):
"""Test a file operations workflow."""
# Create temporary directory for testing
with tempfile.TemporaryDirectory() as temp_dir:
temp_path = Path(temp_dir)
# Create some test files
test_content = "This is test content for the file."
# Process filename through multiple utilities
original_name = "Test File: With Special/Characters!"
safe_name = safe_filename(original_name)
slug_name = slugify(safe_name.rsplit('.', 1)[0]) + '.txt'
# Write file
file_path = temp_path / slug_name
file_path.write_text(test_content)
# Verify file exists and get normalized path
normalized_path = normalize_path(file_path)
assert Path(normalized_path).exists()
# Verify content length matches expectations
content_length = len(test_content)
assert content_length > 0
def test_data_processing_pipeline(self):
"""Test a complete data processing pipeline."""
# Raw data from external source
raw_data = [
{
"userName": "JohnDoe123",
"emailAddress": "john.doe@example.com",
"websiteURL": "https://johndoe.example.com",
"projectVersion": "1.2.0",
"description": "This is a very long description that might need to be truncated for display purposes in certain UI components."
},
{
"userName": "Jane_Smith",
"emailAddress": "invalid-email",
"websiteURL": "not-a-url",
"projectVersion": "invalid-version",
"description": "Short desc"
}
]
processed_data = []
for item in raw_data:
# Convert camelCase to snake_case (would need the function imported)
# For now, just demonstrate with available functions
processed_item = {
"slug": slugify(item["userName"]),
"email_valid": is_valid_email(item["emailAddress"]),
"short_desc": truncate(item["description"], 50),
"safe_filename": safe_filename(f"{item['userName']}_profile.json")
}
processed_data.append(processed_item)
# Verify processing results
assert processed_data[0]["slug"] == "johndoe123"
assert processed_data[0]["email_valid"] is True
assert len(processed_data[0]["short_desc"]) <= 50
assert processed_data[0]["safe_filename"] == "JohnDoe123_profile.json"
assert processed_data[1]["slug"] == "jane-smith"
assert processed_data[1]["email_valid"] is False
assert processed_data[1]["short_desc"] == "Short desc"
assert processed_data[1]["safe_filename"] == "Jane_Smith_profile.json"
def test_configuration_validation(self):
"""Test configuration validation using multiple utilities."""
# Simulate application configuration
config = {
"app_name": "My Application",
"version": "1.0.0",
"admin_email": "admin@myapp.com",
"base_url": "https://myapp.example.com",
"debug": True,
"secret_key": "", # Empty - should be flagged
}
required_fields = ["app_name", "version", "admin_email", "base_url", "secret_key"]
# Validate required fields
validation_result = validate_required_fields(config, required_fields)
assert validation_result["empty"] == ["secret_key"]
# Validate specific formats
email_valid = is_valid_email(config["admin_email"])
assert email_valid is True
# Create safe directory name from app name
app_slug = slugify(config["app_name"])
safe_dir_name = safe_filename(app_slug)
assert app_slug == "my-application"
assert safe_dir_name == "my-application"
# Validate version format would use is_valid_semver
# (assuming we had imported it in the integration test)

View File

@@ -0,0 +1,149 @@
"""
Test suite for string utility functions.
"""
import pytest
from markitect_utils.string_utils import (
slugify,
truncate,
camel_to_snake,
snake_to_camel,
strip_ansi_codes,
)
class TestSlugify:
"""Test cases for the slugify function."""
def test_basic_slugify(self):
"""Test basic string to slug conversion."""
assert slugify("Hello World") == "hello-world"
assert slugify("My Great Article") == "my-great-article"
def test_special_characters(self):
"""Test handling of special characters."""
assert slugify("Hello World!") == "hello-world"
assert slugify("Test@#$%^&*()_+") == "test" # underscore gets converted to separator
assert slugify("Multiple---Dashes") == "multiple-dashes"
def test_custom_separator(self):
"""Test custom separator."""
assert slugify("Hello World", "_") == "hello_world"
assert slugify("My Great Article", ".") == "my.great.article"
def test_edge_cases(self):
"""Test edge cases."""
assert slugify("") == ""
assert slugify(" ") == ""
assert slugify("---") == ""
assert slugify("Single") == "single"
def test_unicode_handling(self):
"""Test unicode character handling."""
assert slugify("Café") == "cafe"
assert slugify("naïve résumé") == "naive-resume"
class TestTruncate:
"""Test cases for the truncate function."""
def test_basic_truncation(self):
"""Test basic string truncation."""
text = "This is a long string that needs truncation"
assert truncate(text, 20) == "This is a long st..."
assert truncate(text, 10) == "This is..."
def test_no_truncation_needed(self):
"""Test when no truncation is needed."""
assert truncate("Short", 10) == "Short"
assert truncate("Exact", 5) == "Exact"
def test_custom_suffix(self):
"""Test custom suffix."""
text = "Long text here"
assert truncate(text, 10, "") == "Long text…"
assert truncate(text, 10, " [more]") == "Lon [more]"
def test_edge_cases(self):
"""Test edge cases."""
assert truncate("", 10) == ""
assert truncate("Test", 3) == "..."
assert truncate("Test", 2) == ".."
assert truncate("Test", 1) == "."
assert truncate("Test", 0) == ""
class TestCamelToSnake:
"""Test cases for the camel_to_snake function."""
def test_basic_conversion(self):
"""Test basic camelCase to snake_case conversion."""
assert camel_to_snake("camelCase") == "camel_case"
assert camel_to_snake("PascalCase") == "pascal_case"
assert camel_to_snake("simpleWord") == "simple_word"
def test_multiple_words(self):
"""Test conversion with multiple words."""
assert camel_to_snake("thisIsALongVariableName") == "this_is_a_long_variable_name"
assert camel_to_snake("XMLHttpRequest") == "xml_http_request"
assert camel_to_snake("JSONData") == "json_data"
def test_edge_cases(self):
"""Test edge cases."""
assert camel_to_snake("") == ""
assert camel_to_snake("single") == "single"
assert camel_to_snake("ALLCAPS") == "allcaps"
assert camel_to_snake("A") == "a"
class TestSnakeToCamel:
"""Test cases for the snake_to_camel function."""
def test_basic_conversion(self):
"""Test basic snake_case to camelCase conversion."""
assert snake_to_camel("snake_case") == "snakeCase"
assert snake_to_camel("simple_word") == "simpleWord"
assert snake_to_camel("single") == "single"
def test_pascal_case(self):
"""Test conversion to PascalCase."""
assert snake_to_camel("snake_case", pascal_case=True) == "SnakeCase"
assert snake_to_camel("simple_word", pascal_case=True) == "SimpleWord"
assert snake_to_camel("single", pascal_case=True) == "Single"
def test_multiple_underscores(self):
"""Test handling of multiple underscores."""
assert snake_to_camel("this_is_a_long_name") == "thisIsALongName"
assert snake_to_camel("this_is_a_long_name", pascal_case=True) == "ThisIsALongName"
def test_edge_cases(self):
"""Test edge cases."""
assert snake_to_camel("") == ""
assert snake_to_camel("_") == ""
assert snake_to_camel("__") == ""
assert snake_to_camel("single") == "single"
class TestStripAnsiCodes:
"""Test cases for the strip_ansi_codes function."""
def test_basic_ansi_removal(self):
"""Test basic ANSI code removal."""
assert strip_ansi_codes("\033[31mRed text\033[0m") == "Red text"
assert strip_ansi_codes("\033[32mGreen\033[0m text") == "Green text"
def test_complex_ansi_codes(self):
"""Test complex ANSI escape sequences."""
text_with_ansi = "\033[1;31;40mBold red on black\033[0m"
assert strip_ansi_codes(text_with_ansi) == "Bold red on black"
def test_no_ansi_codes(self):
"""Test text without ANSI codes."""
plain_text = "Just plain text"
assert strip_ansi_codes(plain_text) == plain_text
def test_edge_cases(self):
"""Test edge cases."""
assert strip_ansi_codes("") == ""
assert strip_ansi_codes("\033[0m") == ""
assert strip_ansi_codes("Start\033[31mMiddle\033[0mEnd") == "StartMiddleEnd"

View File

@@ -0,0 +1,215 @@
"""
Test suite for validation utility functions.
"""
import pytest
from markitect_utils.validation_utils import (
is_valid_email,
is_valid_url,
is_valid_semver,
validate_required_fields,
)
class TestIsValidEmail:
"""Test cases for the is_valid_email function."""
def test_valid_emails(self):
"""Test valid email addresses."""
valid_emails = [
"user@example.com",
"test.email@domain.co.uk",
"user+tag@example.org",
"user123@test-domain.com",
"a@b.co",
]
for email in valid_emails:
assert is_valid_email(email) is True, f"Failed for: {email}"
def test_invalid_emails(self):
"""Test invalid email addresses."""
invalid_emails = [
"invalid.email",
"@example.com",
"user@",
"user@.com",
"user space@example.com",
"user@domain",
"user@@example.com",
"",
]
for email in invalid_emails:
assert is_valid_email(email) is False, f"Should be invalid: {email}"
def test_edge_cases(self):
"""Test edge cases."""
assert is_valid_email(None) is False
assert is_valid_email(123) is False
assert is_valid_email([]) is False
class TestIsValidUrl:
"""Test cases for the is_valid_url function."""
def test_valid_urls(self):
"""Test valid URLs."""
valid_urls = [
"https://example.com",
"http://test.org",
"https://sub.domain.com/path",
"http://localhost:8000",
"https://example.com/path?query=value",
"http://192.168.1.1:3000",
]
for url in valid_urls:
assert is_valid_url(url) is True, f"Failed for: {url}"
def test_invalid_urls(self):
"""Test invalid URLs."""
invalid_urls = [
"not-a-url",
"ftp://example.com",
"example.com",
"://example.com",
"https://",
"http://.com",
"",
]
for url in invalid_urls:
assert is_valid_url(url) is False, f"Should be invalid: {url}"
def test_edge_cases(self):
"""Test edge cases."""
assert is_valid_url(None) is False
assert is_valid_url(123) is False
assert is_valid_url([]) is False
class TestIsValidSemver:
"""Test cases for the is_valid_semver function."""
def test_valid_versions(self):
"""Test valid semantic versions."""
valid_versions = [
"1.0.0",
"0.1.0",
"10.20.30",
"1.0.0-alpha",
"1.0.0-alpha.1",
"1.0.0-0.3.7",
"1.0.0-x.7.z.92",
"1.0.0+20130313144700",
"1.0.0-beta+exp.sha.5114f85",
]
for version in valid_versions:
assert is_valid_semver(version) is True, f"Failed for: {version}"
def test_invalid_versions(self):
"""Test invalid semantic versions."""
invalid_versions = [
"1.0",
"1.0.0-",
"1.0.0+",
"01.0.0",
"1.01.0",
"1.0.01",
"1.0.0-",
"1.0.0+",
"v1.0.0",
"",
]
for version in invalid_versions:
assert is_valid_semver(version) is False, f"Should be invalid: {version}"
def test_edge_cases(self):
"""Test edge cases."""
assert is_valid_semver(None) is False
assert is_valid_semver(123) is False
assert is_valid_semver([]) is False
class TestValidateRequiredFields:
"""Test cases for the validate_required_fields function."""
def test_all_fields_present(self):
"""Test when all required fields are present and valid."""
data = {
"name": "John Doe",
"email": "john@example.com",
"age": 30
}
required = ["name", "email", "age"]
result = validate_required_fields(data, required)
assert result == {"missing": [], "empty": []}
def test_missing_fields(self):
"""Test when some fields are missing."""
data = {
"name": "John Doe",
"email": "john@example.com"
}
required = ["name", "email", "age", "phone"]
result = validate_required_fields(data, required)
assert set(result["missing"]) == {"age", "phone"}
assert result["empty"] == []
def test_empty_fields(self):
"""Test when some fields are empty."""
data = {
"name": "John Doe",
"email": "",
"age": 30,
"phone": " " # whitespace only
}
required = ["name", "email", "age", "phone"]
result = validate_required_fields(data, required)
assert result["missing"] == []
assert set(result["empty"]) == {"email", "phone"}
def test_mixed_issues(self):
"""Test when there are both missing and empty fields."""
data = {
"name": "John Doe",
"email": "",
}
required = ["name", "email", "age", "phone"]
result = validate_required_fields(data, required)
assert set(result["missing"]) == {"age", "phone"}
assert result["empty"] == ["email"]
def test_non_string_values(self):
"""Test with non-string values."""
data = {
"name": "John Doe",
"age": 0, # Zero should not be considered empty
"active": False, # False should not be considered empty
"score": None, # None should be considered empty
"items": [], # Empty list should be considered empty
}
required = ["name", "age", "active", "score", "items"]
result = validate_required_fields(data, required)
assert result["missing"] == []
assert set(result["empty"]) == {"score", "items"}
def test_edge_cases(self):
"""Test edge cases."""
# Invalid inputs
result = validate_required_fields("not a dict", ["field"])
assert result == {"missing": [], "empty": []}
result = validate_required_fields({}, "not a list")
assert result == {"missing": [], "empty": []}
# Empty data and requirements
result = validate_required_fields({}, [])
assert result == {"missing": [], "empty": []}
# Empty requirements
data = {"name": "John"}
result = validate_required_fields(data, [])
assert result == {"missing": [], "empty": []}