refactor(core)!: Add context, config, and structured logging

Introduces `context.Context` to the `FetchCourse` method and its call chain, allowing for cancellable network requests and timeouts. This improves application robustness when fetching remote course data.

A new configuration package centralizes application settings, loading them from environment variables with sensible defaults for base URL, request timeout, and logging.

Standard `log` and `fmt` calls are replaced with a structured logging system built on `slog`, supporting both JSON and human-readable text formats.

This change also includes:
- Extensive benchmarks and example tests.
- Simplified Go doc comments across several packages.

BREAKING CHANGE: The `NewArticulateParser` constructor signature has been updated to accept a logger, base URL, and timeout, which are now supplied via the new configuration system.
This commit is contained in:
2025-11-06 05:14:14 +01:00
parent e6977d3374
commit 37927a36b6
20 changed files with 1409 additions and 104 deletions

View File

@ -0,0 +1,201 @@
// Package exporters_test provides benchmarks for all exporters.
package exporters
import (
"path/filepath"
"testing"
"github.com/kjanat/articulate-parser/internal/models"
"github.com/kjanat/articulate-parser/internal/services"
)
// BenchmarkFactory_CreateExporter_Markdown benchmarks markdown exporter creation.
func BenchmarkFactory_CreateExporter_Markdown(b *testing.B) {
htmlCleaner := services.NewHTMLCleaner()
factory := NewFactory(htmlCleaner)
b.ResetTimer()
for b.Loop() {
_, _ = factory.CreateExporter("markdown")
}
}
// BenchmarkFactory_CreateExporter_All benchmarks creating all exporter types.
func BenchmarkFactory_CreateExporter_All(b *testing.B) {
htmlCleaner := services.NewHTMLCleaner()
factory := NewFactory(htmlCleaner)
formats := []string{"markdown", "docx", "html"}
b.ResetTimer()
for b.Loop() {
for _, format := range formats {
_, _ = factory.CreateExporter(format)
}
}
}
// BenchmarkAllExporters_Export benchmarks all exporters with the same course.
func BenchmarkAllExporters_Export(b *testing.B) {
htmlCleaner := services.NewHTMLCleaner()
course := createBenchmarkCourse()
exporters := map[string]struct {
exporter any
ext string
}{
"Markdown": {NewMarkdownExporter(htmlCleaner), ".md"},
"Docx": {NewDocxExporter(htmlCleaner), ".docx"},
"HTML": {NewHTMLExporter(htmlCleaner), ".html"},
}
for name, exp := range exporters {
b.Run(name, func(b *testing.B) {
tempDir := b.TempDir()
exporter := exp.exporter.(interface {
Export(*models.Course, string) error
})
b.ResetTimer()
for b.Loop() {
outputPath := filepath.Join(tempDir, "benchmark"+exp.ext)
_ = exporter.Export(course, outputPath)
}
})
}
}
// BenchmarkExporters_LargeCourse benchmarks exporters with large course data.
func BenchmarkExporters_LargeCourse(b *testing.B) {
htmlCleaner := services.NewHTMLCleaner()
course := createLargeBenchmarkCourse()
b.Run("Markdown_Large", func(b *testing.B) {
exporter := NewMarkdownExporter(htmlCleaner)
tempDir := b.TempDir()
b.ResetTimer()
for b.Loop() {
outputPath := filepath.Join(tempDir, "large.md")
_ = exporter.Export(course, outputPath)
}
})
b.Run("Docx_Large", func(b *testing.B) {
exporter := NewDocxExporter(htmlCleaner)
tempDir := b.TempDir()
b.ResetTimer()
for b.Loop() {
outputPath := filepath.Join(tempDir, "large.docx")
_ = exporter.Export(course, outputPath)
}
})
b.Run("HTML_Large", func(b *testing.B) {
exporter := NewHTMLExporter(htmlCleaner)
tempDir := b.TempDir()
b.ResetTimer()
for b.Loop() {
outputPath := filepath.Join(tempDir, "large.html")
_ = exporter.Export(course, outputPath)
}
})
}
// createBenchmarkCourse creates a standard-sized course for benchmarking.
func createBenchmarkCourse() *models.Course {
return &models.Course{
ShareID: "benchmark-id",
Author: "Benchmark Author",
Course: models.CourseInfo{
ID: "bench-course",
Title: "Benchmark Course",
Description: "Performance testing course",
NavigationMode: "menu",
Lessons: []models.Lesson{
{
ID: "lesson1",
Title: "Introduction",
Type: "lesson",
Items: []models.Item{
{
Type: "text",
Items: []models.SubItem{
{
Heading: "Welcome",
Paragraph: "<p>This is a test paragraph with <strong>HTML</strong> content.</p>",
},
},
},
{
Type: "list",
Items: []models.SubItem{
{Paragraph: "Item 1"},
{Paragraph: "Item 2"},
{Paragraph: "Item 3"},
},
},
},
},
},
},
}
}
// createLargeBenchmarkCourse creates a large course for stress testing.
func createLargeBenchmarkCourse() *models.Course {
lessons := make([]models.Lesson, 50)
for i := 0; i < 50; i++ {
lessons[i] = models.Lesson{
ID: string(rune(i)),
Title: "Lesson " + string(rune(i)),
Type: "lesson",
Description: "<p>This is lesson description with <em>formatting</em>.</p>",
Items: []models.Item{
{
Type: "text",
Items: []models.SubItem{
{
Heading: "Section Heading",
Paragraph: "<p>Content with <strong>bold</strong> and <em>italic</em> text.</p>",
},
},
},
{
Type: "list",
Items: []models.SubItem{
{Paragraph: "Point 1"},
{Paragraph: "Point 2"},
{Paragraph: "Point 3"},
},
},
{
Type: "knowledgeCheck",
Items: []models.SubItem{
{
Title: "Quiz Question",
Answers: []models.Answer{
{Title: "Answer A", Correct: false},
{Title: "Answer B", Correct: true},
{Title: "Answer C", Correct: false},
},
Feedback: "Good job!",
},
},
},
},
}
}
return &models.Course{
ShareID: "large-benchmark-id",
Author: "Benchmark Author",
Course: models.CourseInfo{
ID: "large-bench-course",
Title: "Large Benchmark Course",
Description: "Large performance testing course",
Lessons: lessons,
},
}
}

View File

@ -0,0 +1,101 @@
// Package exporters_test provides examples for the exporters package.
package exporters_test
import (
"fmt"
"log"
"github.com/kjanat/articulate-parser/internal/exporters"
"github.com/kjanat/articulate-parser/internal/models"
"github.com/kjanat/articulate-parser/internal/services"
)
// ExampleNewFactory demonstrates creating an exporter factory.
func ExampleNewFactory() {
htmlCleaner := services.NewHTMLCleaner()
factory := exporters.NewFactory(htmlCleaner)
// Get supported formats
formats := factory.SupportedFormats()
fmt.Printf("Supported formats: %d\n", len(formats))
// Output: Supported formats: 6
}
// ExampleFactory_CreateExporter demonstrates creating exporters.
func ExampleFactory_CreateExporter() {
htmlCleaner := services.NewHTMLCleaner()
factory := exporters.NewFactory(htmlCleaner)
// Create a markdown exporter
exporter, err := factory.CreateExporter("markdown")
if err != nil {
log.Fatal(err)
}
fmt.Printf("Created: %s exporter\n", exporter.SupportedFormat())
// Output: Created: markdown exporter
}
// ExampleFactory_CreateExporter_caseInsensitive demonstrates case-insensitive format names.
func ExampleFactory_CreateExporter_caseInsensitive() {
htmlCleaner := services.NewHTMLCleaner()
factory := exporters.NewFactory(htmlCleaner)
// All these work (case-insensitive)
formats := []string{"MARKDOWN", "Markdown", "markdown", "MD"}
for _, format := range formats {
exporter, _ := factory.CreateExporter(format)
fmt.Printf("%s -> %s\n", format, exporter.SupportedFormat())
}
// Output:
// MARKDOWN -> markdown
// Markdown -> markdown
// markdown -> markdown
// MD -> markdown
}
// ExampleMarkdownExporter_Export demonstrates exporting to Markdown.
func ExampleMarkdownExporter_Export() {
htmlCleaner := services.NewHTMLCleaner()
exporter := exporters.NewMarkdownExporter(htmlCleaner)
course := &models.Course{
ShareID: "example-id",
Course: models.CourseInfo{
Title: "Example Course",
Description: "<p>Course description</p>",
},
}
// Export to markdown file
err := exporter.Export(course, "output.md")
if err != nil {
log.Fatal(err)
}
fmt.Println("Export complete")
// Output: Export complete
}
// ExampleDocxExporter_Export demonstrates exporting to DOCX.
func ExampleDocxExporter_Export() {
htmlCleaner := services.NewHTMLCleaner()
exporter := exporters.NewDocxExporter(htmlCleaner)
course := &models.Course{
ShareID: "example-id",
Course: models.CourseInfo{
Title: "Example Course",
},
}
// Export to Word document
err := exporter.Export(course, "output.docx")
if err != nil {
log.Fatal(err)
}
fmt.Println("DOCX export complete")
// Output: DOCX export complete
}

View File

@ -33,15 +33,7 @@ func NewFactory(htmlCleaner *services.HTMLCleaner) interfaces.ExporterFactory {
}
// CreateExporter creates an exporter for the specified format.
// It returns an appropriate exporter implementation based on the format string.
// Format strings are case-insensitive.
//
// Parameters:
// - format: The desired export format (e.g., "markdown", "docx")
//
// Returns:
// - An implementation of the Exporter interface if the format is supported
// - An error if the format is not supported
// Format strings are case-insensitive (e.g., "markdown", "DOCX").
func (f *Factory) CreateExporter(format string) (interfaces.Exporter, error) {
switch strings.ToLower(format) {
case "markdown", "md":
@ -55,11 +47,8 @@ func (f *Factory) CreateExporter(format string) (interfaces.Exporter, error) {
}
}
// SupportedFormats returns a list of all supported export formats.
// This includes both primary format names and their aliases.
//
// Returns:
// - A string slice containing all supported format names
// SupportedFormats returns a list of all supported export formats,
// including both primary format names and their aliases.
func (f *Factory) SupportedFormats() []string {
return []string{"markdown", "md", "docx", "word", "html", "htm"}
}

View File

@ -36,16 +36,7 @@ func NewMarkdownExporter(htmlCleaner *services.HTMLCleaner) interfaces.Exporter
}
}
// Export exports a course to Markdown format.
// It generates a structured Markdown document from the course data
// and writes it to the specified output path.
//
// Parameters:
// - course: The course data model to export
// - outputPath: The file path where the Markdown content will be written
//
// Returns:
// - An error if writing to the output file fails
// Export converts the course to Markdown format and writes it to the output path.
func (e *MarkdownExporter) Export(course *models.Course, outputPath string) error {
var buf bytes.Buffer
@ -92,23 +83,13 @@ func (e *MarkdownExporter) Export(course *models.Course, outputPath string) erro
return os.WriteFile(outputPath, buf.Bytes(), 0644)
}
// SupportedFormat returns the format name this exporter supports
// It indicates the file format that the MarkdownExporter can generate.
//
// Returns:
// - A string representing the supported format ("markdown")
// SupportedFormat returns "markdown".
func (e *MarkdownExporter) SupportedFormat() string {
return "markdown"
}
// processItemToMarkdown converts a course item into Markdown format
// and appends it to the provided buffer. It handles different item types
// with appropriate Markdown formatting.
//
// Parameters:
// - buf: The buffer to write the Markdown content to
// - item: The course item to process
// - level: The heading level for the item (determines the number of # characters)
// processItemToMarkdown converts a course item into Markdown format.
// The level parameter determines the heading level (number of # characters).
func (e *MarkdownExporter) processItemToMarkdown(buf *bytes.Buffer, item models.Item, level int) {
headingPrefix := strings.Repeat("#", level)

Binary file not shown.

View File

@ -0,0 +1,12 @@
# Example Course
Course description
## Course Information
- **Course ID**:
- **Share ID**: example-id
- **Navigation Mode**:
---