NodeJS for KF7 CSS Processing

kf7-css.js

#!/usr/bin/env node
// The above "shebang" tells the bash terminal to run this script as a Node.js script.

// Import NodeJS packages
var argv = require('yargs').argv;   // for processing command-line arguments
var fs = require("fs");             // filesystem
var wrench = require('wrench');     // for deep recursive copying
var css = require('css');           // for parsing CSS into an AST
var walk = require('rework-walk'); // for walking ASTs generated by the css module
var cheerio = require('cheerio');   // jquery-like access to an HTML document

// Define an "ends with" method that is useful later.
if (typeof String.prototype.endsWith !== 'function') {
    String.prototype.endsWith = function(suffix) {
        return this.indexOf(suffix, this.length - suffix.length) !== -1;
    };
}

// Fetches all files in a folder, recursively
function filesRecursive(dir) {
    var results = [];
    var list = fs.readdirSync(dir);
    list.forEach(function(file) {
        file = dir + '/' + file;
        var stat = fs.statSync(file);
        if (stat && stat.isDirectory()) {
            results = results.concat(walk(file));
        } else {
            results.push(file);  
        } 
    });
    return results;
}

// Same as filesRecursive, but filters for files that end with an ext, such as ".css"
function filesRecursiveWithExt(dir, ext){
    var results = walk(dir);
    return results.reduce(function(filteredContents, filename){
        if (filename.endsWith(ext)) {
            filteredContents.push(filename);
        }
        return filteredContents;
    }, []);
}

// Convenience function: 
// reads a file, calls a function that you give it, 
// and then writes back to the file whatever your function returns
function readWrite(filePath, callback){
    var content = '';
    var stats = fs.statSync(filePath);
    if (!stats.isDirectory()) {
        content = fs.readFileSync(filePath).toString();
    }
    if (callback) {
        content = callback(content, stats);
        if (!stats.isDirectory() && content) {
            fs.writeFileSync(filePath, content);
        }
    } else {
        return content;
    }
}

/////////////////////
// MAIN SCRIPT STARTS
/////////////////////

// Get the path to the epub directory, as an argument
var targetDirectory = argv._[0];
if (!targetDirectory) {
    console.log("Please specify the directory of the epub you want to work with.");

}
var scriptDir = path.dirname(require.main.filename); // current directory of the main script
var resolvedTargetDir = path.resolve(targetDirectory);

// Clone the directory so we don't taint the original
var newDirectory = resolvedTargetDir + '_kf7';
wrench.copyDirSyncRecursive(resolvedTargetDir, newDirectory, {
    forceDelete: true // overwrites any "_kf7" directory that's already there
});

// Simplify our CSS rules
var complexSelectorMap = {};
var cssFiles = filesRecursiveWithExt(newDirectory, "css");
cssFiles.forEach(function(filename){
    readWrite(filename, function(content, stats){
        if (!content) return;

        // Parse the CSS into an AST that can be walked
        var ast = css.parse(content);

        // Walk the AST
        walk(ast.stylesheet, function(rule, node){

            if (!rule.selectors) return;

            var remove = [];
            var add = [];
            rule.selectors.forEach(function(sel, idx){

                // If the selector contains a space, it's too complex for Kindlegen
                var parts = sel.split(" ");
                if (parts.length > 1) {

                    // Create a simplified version of the selector
                    var newSel = '.' + parts.join('-').replace('#', '-id-').replace('.', '-clz-').replace('+', '-adj-').replace('~', '-pre-').replace('[', '-lbr-').replace(']', '-rbr-').replace(/-{2,}/, '-');

                    // Add it to our list to add to this rule
                    add.push(newSel);

                    // Map the complex selector to the simplified version (for later adjustments we do in the markup)
                    complexSelectorMap[sel] = newSel;

                    // Add this selector to our list to remove
                    remove.push(idx);
                }
            });

            // Remove the complex selectors, if any.
            // Note that we go backwards through the list, otherwise our indexes will be messed up.
            for (var i = remove.length - 1; i >= 0; i--) {
                rule.selectors.splice(remove[i], 1);
            };

            // Add the simplified selectors, if any
            rule.selectors = rule.selectors.concat(add);

        });

        // Stringify the modified AST and return it, so it gets written back to the file
        return css.stringify(ast);
    });
});

// Now convert everything in the markup to the simpler selectors, as it were
var compoundClassMap = {};
var htmlFiles = filesRecursiveWithExt(newDirectory, "html"); // will include "xhtml"
htmlFiles.forEach(function(filename){
    readWrite(filename, function(content, stats){
        if (!content) return;

        // Load up everything into Cheerio!
        var $ = cheerio.load(content, {
            xmlMode: true
        });

        // Find everything that the complex selectors applied to, and stick the simpler class on them
        Object.keys(complexSelectorMap).forEach(function(key) {
            $(key).addClass(complexSelectorMap[key]); // ...Well, that was easy.
        });

        return $.xml();
    });
});

More fully fledged version: https://github.com/allscribe/allscribe