hdoc-tools 0.6.0 → 0.6.1

package/hdoc-init.js

@@ -0,0 +1,36 @@
+(function () {
+    'use strict';
+
+    const prompt = require('prompt');
+
+    const properties = [{
+            name: 'documentId',
+            validator: /^[a-z-]+$/,
+            warning: 'Document ID must only contain lower case letters and dashes'
+        },
+        {
+            name: 'title'
+        },
+        {
+            name: 'initialVersion',
+            validator: /^[a-z-]+$/,
+            warning: 'Document ID must only contain lower case letters and dashes'
+        }
+    ];
+
+    exports.run = function (ui_path, source_path, md) {
+
+        // GERRY: The init function should create a new starting point HDocBook folder structure
+        // ready to run the preview server and start editing. 
+        //
+        // The init function should prompt for the ID of the doc book, title and initial version, then
+        // create the required files and folders.  Its possible to just create a template and copy
+        // those files into place, with a few variable replacements. 
+        // 
+        // 
+
+        console.log("Init is not yet implemented");
+
+
+    };
+})();

package/hdoc-stats.js

@@ -0,0 +1,146 @@
+
+(function () {
+    'use strict';
+    
+    // Required modules
+    const { STATUS_CODES } = require('http');
+    const fs = require('fs');
+    const dree = require('dree');
+    const html2text = require('html-to-text');
+    const { markdownToTxt } = require('markdown-to-txt');
+    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;
+    
+    let stats = {
+        totalMDFiles: 0,
+        totalStaticHTMLFiles: 0,
+        totalWordCount: 0,
+        mdFiles: {},
+        staticHTMLFiles: {} 
+    };
+    // File callback for scan
+    const fileCallback = function(element) {
+        if (element.extension === 'md' ) {
+            
+            // Read markdown file as string
+            const md = fs.readFileSync(element.path, 'utf8');
+            
+            // Strip out standard MD tags
+            let text = markdownToTxt(md);
+            
+            // Strip out any Hornbill Docs specific markdown tags 
+            text = text.replaceAll(hbMDTagRegex, '');
+            
+            // Do the wordcount and add to status
+            const wordCount = wordsCount(text);
+            stats.totalWordCount += wordCount;
+            stats.mdFiles[element.relativePath] = {
+                wordCount: wordCount,
+                sizeInBytes: element.sizeInBytes
+            };
+            stats.totalMDFiles++;
+        } else {
+            // file must be html
+            const mdFilePath = element.path.slice(0, element.path.lastIndexOf('.')) + '.md';
+            if (!fs.existsSync(mdFilePath)) {
+                //Do we have a matching MD file - if not, then word count the HTML
+                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, md, 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
+        console.log('Hornbill HDocBook Stats', '\r\n');
+
+        // 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
+        
+        const project_json_path = 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: ', e);
+                return;
+            }
+
+            // Scan content path directory, send file info to callback for processing
+            dree.scan(source_path + '/' + book_details.docId, dreeOptions, fileCallback);
+            
+            if (verbose) {
+                // Output verbose stats 
+
+                // Output information about all markdown files in the book
+                console.log('--------------');
+                console.log('   Markdown   ');
+                console.log('--------------');
+                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  ');
+                console.log('---------------');
+                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('  Total Book Word Count: ' + stats.totalWordCount);
+            console.log('         Markdown Files: ' + stats.totalMDFiles);
+            console.log('      Static HTML Files: ' + stats.totalStaticHTMLFiles + '\r\n');
+
+        }
+    };
+})();

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "hdoc-tools",
-  "version": "0.6.0",
+  "version": "0.6.1",
   "description": "Hornbill HDocBook Development Support Tool",
   "main": "hdoc.js",
   "bin": {
@@ -9,6 +9,8 @@
   "files": [
     "hdoc.js",
     "hdoc-serve.js",
+    "hdoc-stats.js",
+    "hdoc-init.js",
     "hdoc-build.js",
     "ui",
     "custom_modules"