mirror of
https://github.com/kjanat/articulate-parser.git
synced 2026-01-16 07:02:09 +01:00
Kaj Kowalski
2790064ad5
Removes the `Get` prefix from exporter methods (e.g., GetSupportedFormat -> SupportedFormat) to better align with Go conventions for simple accessors. Introduces `context.Context` propagation through the application, starting from `ProcessCourseFromURI` down to the HTTP request in the parser. This makes network operations cancellable and allows for setting deadlines, improving application robustness. Additionally, optimizes the HTML cleaner by pre-compiling regular expressions for a minor performance gain.
60 lines
2.2 KiB
Go
60 lines
2.2 KiB
Go
// Package services provides the core functionality for the articulate-parser application.
|
|
// It implements the interfaces defined in the interfaces package.
|
|
package services
|
|
|
|
import (
|
|
"regexp"
|
|
"strings"
|
|
)
|
|
|
|
var (
|
|
// htmlTagRegex matches HTML tags for removal
|
|
htmlTagRegex = regexp.MustCompile(`<[^>]*>`)
|
|
// whitespaceRegex matches multiple whitespace characters for normalization
|
|
whitespaceRegex = regexp.MustCompile(`\s+`)
|
|
)
|
|
|
|
// HTMLCleaner provides utilities for converting HTML content to plain text.
|
|
// It removes HTML tags while preserving their content and converts HTML entities
|
|
// to their plain text equivalents.
|
|
type HTMLCleaner struct{}
|
|
|
|
// NewHTMLCleaner creates a new HTML cleaner instance.
|
|
// This service is typically injected into exporters that need to handle
|
|
// HTML content from Articulate Rise courses.
|
|
func NewHTMLCleaner() *HTMLCleaner {
|
|
return &HTMLCleaner{}
|
|
}
|
|
|
|
// CleanHTML removes HTML tags and converts entities, returning clean plain text.
|
|
// The function preserves the textual content of the HTML while removing markup.
|
|
// It handles common HTML entities like , &, etc., and normalizes whitespace.
|
|
//
|
|
// Parameters:
|
|
// - html: The HTML content to clean
|
|
//
|
|
// Returns:
|
|
// - A plain text string with all HTML elements and entities removed/converted
|
|
func (h *HTMLCleaner) CleanHTML(html string) string {
|
|
// Remove HTML tags but preserve content
|
|
cleaned := htmlTagRegex.ReplaceAllString(html, "")
|
|
|
|
// Replace common HTML entities with their character equivalents
|
|
cleaned = strings.ReplaceAll(cleaned, " ", " ")
|
|
cleaned = strings.ReplaceAll(cleaned, "&", "&")
|
|
cleaned = strings.ReplaceAll(cleaned, "<", "<")
|
|
cleaned = strings.ReplaceAll(cleaned, ">", ">")
|
|
cleaned = strings.ReplaceAll(cleaned, """, "\"")
|
|
cleaned = strings.ReplaceAll(cleaned, "'", "'")
|
|
cleaned = strings.ReplaceAll(cleaned, "ï", "ï")
|
|
cleaned = strings.ReplaceAll(cleaned, "ë", "ë")
|
|
cleaned = strings.ReplaceAll(cleaned, "é", "é")
|
|
|
|
// Clean up extra whitespace by replacing multiple spaces, tabs, and newlines
|
|
// with a single space, then trim any leading/trailing whitespace
|
|
cleaned = whitespaceRegex.ReplaceAllString(cleaned, " ")
|
|
cleaned = strings.TrimSpace(cleaned)
|
|
|
|
return cleaned
|
|
}
|