Convert .tex file to .html (simple cases)

convert_tex_to_html.sh

#!/bin/bash

# Input and output files
input_file="input.tex"
output_file="output.html"

# Function to remove curly braces
remove_braces() {
    echo "$1" | sed 's/[{}]//g'
}

# Flag to track if we are inside a tcblisting block
inside_tcblisting=0

# Process the LaTeX file
while IFS= read -r line
do
    # Check for tcblisting environment
    if [[ "$line" == "\\begin{tcblisting}"* ]]; then
        inside_tcblisting=1
        continue
    elif [[ "$line" == "\\end{tcblisting}" ]]; then
        inside_tcblisting=0
        continue
    fi

    # Skip processing lines inside tcblisting blocks
    if [ $inside_tcblisting -eq 1 ]; then
        continue
    fi

    # Remove braces
    line=$(remove_braces "$line")

    # Replace \chapter, \section, and \subsection with corresponding HTML tags
    if [[ "$line" =~ ^\\chapter\*(.*) ]]; then
        echo "<h1>${BASH_REMATCH[1]}</h1>" >> "$output_file"
    elif [[ "$line" =~ ^\\chapter(.*) ]]; then
        echo "<h1>${BASH_REMATCH[1]}</h1>" >> "$output_file"
    elif [[ "$line" =~ ^\\section(.*) ]]; then
        echo "<h2>${BASH_REMATCH[1]}</h2>" >> "$output_file"
    elif [[ "$line" =~ ^\\subsection(.*) ]]; then
        echo "<h3>${BASH_REMATCH[1]}</h3>" >> "$output_file"
    elif [[ "$line" =~ ^\\subsubsection(.*) ]]; then
        echo "<h4>${BASH_REMATCH[1]}</h4>" >> "$output_file"
    else
        # Check if the line starts with "-" and wrap it with <li> tags
	if [[ "$line" == " - "* || "$line" == "-"* || "$line" == " -"* ]]; then
            # Add <li> tags around the line, removing the leading "-" character
            echo "<li>${line:3}</li>" >> "$output_file"
        else
            # Wrap other lines in <p> tags if they're not empty
            if [[ ! -z "$line" ]]; then
                echo "$line" >> "$output_file"
            fi
        fi
    fi
done < "$input_file"

echo "Conversion complete. Output is in $output_file"