Flag/API methods for excluding directories and file reading options

.gitignore

@@ -1 +1,3 @@
-/node_modules
+/node_modules
+.npmignore
+npm-debug.log

README.md

@@ -11,10 +11,34 @@ $ npm install hugo-lunr
 ```
 
 ## Options
-By default hugo-lunr will read the `content` directory of you and output the lunr index to `public/lunr.json`. If you are using the command line implementation you can pass an input directory `-i` and and output path/file `-o`.
+By default hugo-lunr will read the `content` directory of you and output the lunr index to `public/lunr.json`. If you are using the command line implementation you can pass an input directory `-i` and an output path/file `-o`.
 
+### Exclude folders
+
+To exclude folders within your input directory, you can pass comma-separated [glob patterns](https://www.npmjs.com/package/glob#glob-primer) with the `--excludes` parameter, e.g.
+
+```
+hugo-lunr -i \"content/subdir/**\" -o public/my-index.json --excludes \"content/images/**\"
+```
+
+Note that the API version of this flag (`setExcludes()`) can accept a comma-separated string or an array of glob patterns.
+
+### Content file options
+
+Using the `--fileopts` CLI flag or `setFileOpts()` API method, you can specify these options when reading content files:
+
+| Key | Default | Desc |
+| --- | --- | --- |
+| `matter` | `{delims: '+++', lang:'toml'}` | [Options](https://www.npmjs.com/package/gray-matter#read) for reading front matter |
+| `taxonomies` | `['tags']` | Array of taxonomies to include in index |
+| `indexDrafts` | `false` | Whether to include draft posts when building search index. Note that **future-dated posts will be indexed** (PRs welcome...) |
+| `params` | `[]` | Array of any other parameters to include in index, e.g. `date` |
+| `callback` | null | Callback function to transform the output of reading each file. Can be used only with API |
+
+You can provide the path to a JSON file using CLI flag or API, or just pass an object directly when calling the API method.
 
 ## How to use hugo-lunr CLI
+
 The easiest way to use hugo-lunr is via npm scripts:
 ```
   "scripts": {
@@ -48,7 +72,7 @@ var hugolunr = require('hugo-lunr');
 var h = new hugolunr();
 h.setInput('content/faq/**');
 h.setOutput('public/faq.json');
+h.setExcludes(['content/faq/images/**', 'content/faq/subdir/assets/**']);
+h.setFileOpts({ taxonomies: ['tags', 'categories'] });
 h.index();
 ```
-
-

lib/index.js

@@ -21,6 +21,16 @@ function HugoLunr(input, output){
 	//defaults
 	this.input = 'content/**';
 	this.output = 'public/lunr.json';
+	this.excludes = [];
+
+	// Default file reading options
+	this.fileOpts = {
+		matter: {delims: '+++', lang:'toml'},
+		taxonomies: ['tags'],
+		indexDrafts: false,
+		params: [],
+		callback: null
+	};
 
  	if(process.argv.indexOf("-o") != -1){ //does output flag exist?
 		this.setOutput(process.argv[process.argv.indexOf("-o") + 1]); //grab the next item
@@ -30,17 +40,56 @@ function HugoLunr(input, output){
 	    this.setInput(process.argv[process.argv.indexOf("-i") + 1]); //grab the next item
 	}
 
+	if(process.argv.indexOf("--excludes") != -1){ //does excludes flag exist?
+	    this.setExcludes(process.argv[process.argv.indexOf("--excludes") + 1]); //grab the next item
+	}
+
+	if(process.argv.indexOf("--fileopts") != -1){ //does fileopts flag exist?
+	    this.setFileOpts(process.argv[process.argv.indexOf("--fileopts") + 1]); //grab the next item
+	}
+
 	this.baseDir = path.dirname(this.input);
 }
 
 HugoLunr.prototype.setInput = function(input) {
 	this.input = input;
+	this.baseDir = path.dirname(input);
 }
 
 HugoLunr.prototype.setOutput = function(output) {
 	this.output = output;
 }
 
+HugoLunr.prototype.setExcludes = function(excludes) {
+	// Comma-separated array of glob paths from --excludes arg
+	// Or array if using API
+	this.excludes = typeof excludes === 'string' ? excludes.split(',') : excludes;
+}
+
+HugoLunr.prototype.setFileOpts = function(opts) {
+	// If string assume path to opts JSON file
+	// otherwise assume object was passed to API
+	var optsObj = opts;
+	if ('string' === typeof opts) {
+		try {
+			var filename = path.resolve(path.dirname(process.argv[1]), opts);
+			optsObj = JSON.parse(fs.readFileSync(filename, 'utf8'));
+		} catch (e)  {
+			optsObj = null;
+		}
+	}
+
+	if (!optsObj) {
+		return;
+	}
+
+	// Merge into this.fileOpts
+	var self = this;
+	Object.keys(optsObj).forEach(function(key) {
+		self.fileOpts[key] = optsObj[key];
+	});
+}
+
 HugoLunr.prototype.index = function(input, output){
 	var self = this;
 
@@ -62,7 +111,7 @@ HugoLunr.prototype.index = function(input, output){
 
 HugoLunr.prototype.readDirectory = function(path){
 	var self = this;
-	var files = glob.sync(path);
+	var files = glob.sync(path, { ignore: this.excludes });
 	var len = files.length;
 	for (var i=0;i<len;i++){
 		var stats = fs.lstatSync(files[i]);
@@ -76,39 +125,46 @@ HugoLunr.prototype.readDirectory = function(path){
 HugoLunr.prototype.readFile = function(filePath){
 	var self = this;
 	var ext = path.extname(filePath);
-	var meta = matter.read(filePath, {delims: '+++', lang:'toml'});
-	if (meta.data.draft === true){
+	var meta = matter.read(filePath, self.fileOpts.matter);
+	if (meta.data.draft === true && !self.fileOpts.indexDrafts){
 		return;
 	}
 
-	if (ext == '.md'){
-		var plainText = removeMd(meta.content);
+	// Setup title and content
+	var item = {
+		title: meta.data.title || '',
+		content: ext == '.md' ? removeMd(meta.content) : striptags(meta.content)
+	};
+
+	// Setup URI
+	if (meta.data.url != undefined){
+		item.uri = meta.data.url;
 	} else {
-		var plainText = striptags(meta.content);
-	}
+		var uri = '/' + filePath.substring(0,filePath.lastIndexOf('.'));
+		uri = uri.replace(self.baseDir +'/', '');
 
-	var uri = '/' + filePath.substring(0,filePath.lastIndexOf('.'));
-	uri = uri.replace(self.baseDir +'/', '');
+		if (meta.data.slug !=  undefined){
+			uri = path.dirname(uri) + meta.data.slug;
+		}
 
-	if (meta.data.slug !=  undefined){
-		uri = path.dirname(uri) + meta.data.slug;
+		item.uri = uri;
 	}
 
-	if (meta.data.url != undefined){
-		uri = meta.data.url
-	}
+	// Setup taxonomies
+	self.fileOpts.taxonomies.forEach(function(taxonomy) {
+		item[taxonomy] = meta.data[taxonomy] || [];
+	});
 
-	var tags = [];
+	// Setup additional specified params
+	if (self.fileOpts.params.length) {
+		self.fileOpts.params.forEach(function(param) {
+			item[param] = meta.data[param] || null;
+		});
+	}
 
-	if (meta.data.tags != undefined){
-		tags = meta.data.tags;
+	if ('function' === typeof self.fileOpts.callback) {
+		item = self.fileOpts.callback(item);
 	}
 
-	var item = {'uri' : uri , 'title' : meta.data.title, 'content':plainText, 'tags':tags};
 	self.list.push(item);
 }
-
-
-
-
-