hdoc-tools 0.19.7 → 0.20.0

package/hdoc-stats.js

@@ -1,184 +1,187 @@
-
-(function () {
-    'use strict';
-
-    // Required modules
-    // /const { STATUS_CODES } = require('http');
-    const fs = require('fs'),
-        path = require('path'),
-        dree = require('dree'),
-        html2text = require('html-to-text'),
-        wordsCount = require('words-count').default;
-
-    // Regex to remove Hornbill-specific tags 
-    const hbMDTagRegex = /(:{3}[ ]note)|(:{3}[ ]tip)|(:{3}[ ]important)|(:{3}[ ]caution)|(:{3}[ ]warning)|(:{3})/g;
-
-    let stats = {
-        totalMDFiles: 0,
-        totalStaticHTMLFiles: 0,
-        totalWordCount: 0,
-        mdFiles: {},
-        staticHTMLFiles: {}
-    };
-
-    let markdownFiles = [];
-
-    // File callback for scan 
-    const fileCallback = function (element) {
-        if (element.extension === 'md') {
-            markdownFiles.push(element);
-            stats.totalMDFiles++;
-        } else {
-            // file must be html
-            const mdFilePath = element.path.slice(0, element.path.lastIndexOf('.')) + '.md';
-            //Do we have a matching MD file - if not, then word count the HTML
-            if (!fs.existsSync(mdFilePath)) {
-                stats.totalStaticHTMLFiles++;
-                const html = fs.readFileSync(element.path, 'utf8');
-                const text = html2text.convert(html, {
-                    wordwrap: null
-                });
-                const wordCount = wordsCount(text);
-                stats.totalWordCount += wordCount;
-                stats.staticHTMLFiles[element.relativePath] = {
-                    wordCount: wordCount,
-                    sizeInBytes: element.sizeInBytes
-                };
-            }
-        }
-    };
-
-    const dreeOptions = {
-        descendants: true,
-        depth: 10,
-        extensions: ['md', 'html', 'htm'],
-        hash: false,
-        normalize: true,
-        size: true,
-        sizeInBytes: true,
-        stat: false,
-        symbolicLinks: false
-    };
-
-    exports.run = function (ui_path, source_path, verbose = false) {
-
-        // GERRY: The stats here are needed to support content development. The idea is to count all of the ]
-        // words in a HDocBook so we know the size of the book, this helps with 3rd party involvement where
-        // we generally need to know the word count of the content in order to get a quote for things like
-        // copy editing. reviewing and translations. 
-        //
-        // For each .md file, and for each static .HTML file (that is html files that we have not generated) we
-        // should do a word count, excluding MD or HTML tags
-
-        // STEVE: Get the docId (book root) from the hdocbook-project.json
-        // From there, loop through looking for:
-        // * HTML files without a matching MD, and word count those
-        // * MD files, and word count those
-
-
-        console.log('Hornbill HDocBook Stats : verbose=' + verbose, '\r\n');
-
-        const project_json_path = path.join(source_path, 'hdocbook-project.json');
-
-        if (!fs.existsSync(project_json_path)) {
-            // Book config does not exist
-            console.error('Required project file does not exist:', project_json_path);
-            return;
-        } else {
-            // Book config exists - load book details 
-            let book_details;
-            try {
-                book_details = JSON.parse(fs.readFileSync(project_json_path, 'utf8'));
-            } catch (e) {
-                console.error('Error reading book configuration:\r\n', e);
-                return;
-            }
-            const bookPath = path.join(source_path, book_details.docId);
-
-            //Load book config
-            let bookConfig;
-            try {
-                bookConfig = JSON.parse(fs.readFileSync(path.join(bookPath, 'hdocbook.json'), 'utf8'));
-            } catch (e) {
-                console.error('Could not load book configuration:\r\n', e);
-                return;
-            }
-            // Load markdown-it module
-            const md = require('markdown-it')({
-                html: true,
-                linkify: true,
-                typographer: true
-            });
-
-            // Scan content path directory, send file info to callback for processing
-            dree.scan(bookPath, dreeOptions, fileCallback);
-            markdownFiles.forEach(function (element) {
-                // Load markdown file
-                let md_txt = fs.readFileSync(element.path, 'utf8');
-
-                var html_txt = md.render(md_txt.toString());
-                const text = html2text.convert(html_txt, {
-                    wordwrap: null
-                });
-
-                // Do the wordcount and add to status
-                const wordCount = wordsCount(text);
-                stats.totalWordCount += wordCount;
-                stats.mdFiles[element.relativePath] = {
-                    wordCount: wordCount,
-                    sizeInBytes: element.sizeInBytes
-                };
-            });
-
-            if (verbose) {
-                // Output verbose stats 
-
-                // Output information about all markdown files in the book
-                console.log('--------------------');
-                console.log('   Markdown Files   ');
-                console.log('--------------------\r\n');
-                if (stats.totalMDFiles === 0) {
-                    console.log('No markdown files found.\r\n');
-                } else {
-                    for (const key in stats.mdFiles) {
-                        if (stats.mdFiles.hasOwnProperty(key)) {
-                            console.log('Relative Path:', key);
-                            console.log('   Word Count:', stats.mdFiles[key].wordCount);
-                            console.log('File Size (B):', stats.mdFiles[key].sizeInBytes, '\r\n');
-                        }
-                    }
-                }
-
-                // Output information about all static HTML in the book
-                console.log('-----------------------');
-                console.log('   Static HTML Files   ');
-                console.log('-----------------------\r\n');
-                if (stats.totalStaticHTMLFiles === 0) {
-                    console.log('No static HTML files found.\r\n');
-                } else {
-                    for (const key in stats.staticHTMLFiles) {
-                        if (stats.staticHTMLFiles.hasOwnProperty(key)) {
-                            console.log('Relative Path:', key);
-                            console.log('   Word Count:', stats.staticHTMLFiles[key].wordCount);
-                            console.log('File Size (B):', stats.staticHTMLFiles[key].sizeInBytes, '\r\n');
-                        }
-                    }
-                }
-            }
-
-            // Output stats
-            console.log('----------------------');
-            console.log('   Book Information   ');
-            console.log('----------------------\r\n');
-            console.log('          Document ID:', bookConfig.docId);
-            console.log('              Version:', bookConfig.version, '\r\n');
-            console.log('                Title:', bookConfig.title);
-            console.log('          Description:', bookConfig.description);
-            console.log('        Public Source:', bookConfig.publicSource, '\r\n');
-            console.log('Total Book Word Count:', stats.totalWordCount);
-            console.log('       Markdown Files:', stats.totalMDFiles);
-            console.log('    Static HTML Files:', stats.totalStaticHTMLFiles, '\r\n');
-
-        }
-    };
-})();
+(() => {
+	// Required modules
+	const fs = require("node:fs");
+	const path = require("node:path");
+	const dree = require("dree");
+	const html2text = require("html-to-text");
+	const wordsCount = require("words-count").default;
+
+	// Regex to remove Hornbill-specific tags
+	const hbMDTagRegex =
+		/(:{3}[ ]note)|(:{3}[ ]tip)|(:{3}[ ]important)|(:{3}[ ]caution)|(:{3}[ ]warning)|(:{3})/g;
+
+	const stats = {
+		totalMDFiles: 0,
+		totalStaticHTMLFiles: 0,
+		totalWordCount: 0,
+		mdFiles: {},
+		staticHTMLFiles: {},
+	};
+
+	const markdownFiles = [];
+
+	// File callback for scan
+	const fileCallback = (element) => {
+		if (element.extension === "md") {
+			markdownFiles.push(element);
+			stats.totalMDFiles++;
+		} else {
+			// file must be html
+			const mdFilePath = `${element.path.slice(0, element.path.lastIndexOf("."))}.md`;
+			//Do we have a matching MD file - if not, then word count the HTML
+			if (!fs.existsSync(mdFilePath)) {
+				stats.totalStaticHTMLFiles++;
+				const html = fs.readFileSync(element.path, "utf8");
+				const text = html2text.convert(html, {
+					wordwrap: null,
+				});
+				const wordCount = wordsCount(text);
+				stats.totalWordCount += wordCount;
+				stats.staticHTMLFiles[element.relativePath] = {
+					wordCount: wordCount,
+					sizeInBytes: element.sizeInBytes,
+				};
+			}
+		}
+	};
+
+	const dreeOptions = {
+		descendants: true,
+		depth: 10,
+		extensions: ["md", "html", "htm"],
+		hash: false,
+		normalize: true,
+		size: true,
+		sizeInBytes: true,
+		stat: false,
+		symbolicLinks: false,
+	};
+
+	exports.run = (ui_path, source_path, verbose = false) => {
+		// GERRY: The stats here are needed to support content development. The idea is to count all of the ]
+		// words in a HDocBook so we know the size of the book, this helps with 3rd party involvement where
+		// we generally need to know the word count of the content in order to get a quote for things like
+		// copy editing. reviewing and translations.
+		//
+		// For each .md file, and for each static .HTML file (that is html files that we have not generated) we
+		// should do a word count, excluding MD or HTML tags
+
+		// STEVE: Get the docId (book root) from the hdocbook-project.json
+		// From there, loop through looking for:
+		// * HTML files without a matching MD, and word count those
+		// * MD files, and word count those
+
+		console.log(`Hornbill HDocBook Stats : verbose=${verbose}\r\n`);
+
+		const project_json_path = path.join(source_path, "hdocbook-project.json");
+
+		if (!fs.existsSync(project_json_path)) {
+			// Book config does not exist
+			console.error("Required project file does not exist:", project_json_path);
+			return;
+		}
+		// Book config exists - load book details
+		let book_details;
+		try {
+			book_details = JSON.parse(fs.readFileSync(project_json_path, "utf8"));
+		} catch (e) {
+			console.error("Error reading book configuration:\r\n", e);
+			return;
+		}
+		const bookPath = path.join(source_path, book_details.docId);
+
+		//Load book config
+		let bookConfig;
+		try {
+			bookConfig = JSON.parse(
+				fs.readFileSync(path.join(bookPath, "hdocbook.json"), "utf8"),
+			);
+		} catch (e) {
+			console.error("Could not load book configuration:\r\n", e);
+			return;
+		}
+		// Load markdown-it module
+		const md = require("markdown-it")({
+			html: true,
+			linkify: true,
+			typographer: true,
+		});
+
+		// Scan content path directory, send file info to callback for processing
+		dree.scan(bookPath, dreeOptions, fileCallback);
+		for (const element of markdownFiles) {
+			// Load markdown file
+			const md_txt = fs.readFileSync(element.path, "utf8");
+
+			const html_txt = md.render(md_txt.toString());
+			const text = html2text.convert(html_txt, {
+				wordwrap: null,
+			});
+
+			// Do the wordcount and add to status
+			const wordCount = wordsCount(text);
+			stats.totalWordCount += wordCount;
+			stats.mdFiles[element.relativePath] = {
+				wordCount: wordCount,
+				sizeInBytes: element.sizeInBytes,
+			};
+		}
+
+		if (verbose) {
+			// Output verbose stats
+
+			// Output information about all markdown files in the book
+			console.log("--------------------");
+			console.log("   Markdown Files   ");
+			console.log("--------------------\r\n");
+			if (stats.totalMDFiles === 0) {
+				console.log("No markdown files found.\r\n");
+			} else {
+				for (const key in stats.mdFiles) {
+					if (Object.hasOwn(stats.mdFiles, key)) {
+						console.log("Relative Path:", key);
+						console.log("   Word Count:", stats.mdFiles[key].wordCount);
+						console.log(
+							"File Size (B):",
+							stats.mdFiles[key].sizeInBytes,
+							"\r\n",
+						);
+					}
+				}
+			}
+
+			// Output information about all static HTML in the book
+			console.log("-----------------------");
+			console.log("   Static HTML Files   ");
+			console.log("-----------------------\r\n");
+			if (stats.totalStaticHTMLFiles === 0) {
+				console.log("No static HTML files found.\r\n");
+			} else {
+				for (const key in stats.staticHTMLFiles) {
+					if (Object.hasOwn(stats.staticHTMLFiles, key)) {
+						console.log("Relative Path:", key);
+						console.log("   Word Count:", stats.staticHTMLFiles[key].wordCount);
+						console.log(
+							"File Size (B):",
+							stats.staticHTMLFiles[key].sizeInBytes,
+							"\r\n",
+						);
+					}
+				}
+			}
+		}
+
+		// Output stats
+		console.log("----------------------");
+		console.log("   Book Information   ");
+		console.log("----------------------\r\n");
+		console.log("          Document ID:", bookConfig.docId);
+		console.log("              Version:", bookConfig.version, "\r\n");
+		console.log("                Title:", bookConfig.title);
+		console.log("          Description:", bookConfig.description);
+		console.log("        Public Source:", bookConfig.publicSource, "\r\n");
+		console.log("Total Book Word Count:", stats.totalWordCount);
+		console.log("       Markdown Files:", stats.totalMDFiles);
+		console.log("    Static HTML Files:", stats.totalStaticHTMLFiles, "\r\n");
+	};
+})();