Avoid analyzing excluded language files for line counting

This change passes in a list of file types to the line counting
analysis. These are the languages for the databases being analyzed.
Line count analysis is restricted to these files.

node_modules/github-linguist/src/cli.ts

@@ -2,9 +2,6 @@
 
 import chalk from 'chalk';
 import program from 'commander';
-// @ts-ignore
-import slash from 'slash2';
-import path from 'path';
 
 import { LocDir } from './directory';
 import { LocFile, LineInfo } from './file';

node_modules/github-linguist/src/directory.ts

@@ -5,6 +5,7 @@ import path from 'path';
 import slash from 'slash2';
 
 import { LineInfo, LocFile } from './file';
+import { Languages } from './languages';
 
 const defaultInfo: LineInfo = {
   total: 0,
@@ -16,6 +17,7 @@ export interface LocDirOptions {
   cwd?: string;
   include?: string[] | string;
   exclude?: string[] | string;
+  analysisLanguages?: string[];
 }
 
 export interface LocResult {
@@ -38,7 +40,86 @@ const defaultExclude = [
   '**/*.snap',
 
   // java
-  '**/target'
+  '**/target',
+  "**/*.class",
+  "**/*.o",
+  "**/bin",
+  "**/*.map",
+
+  // python
+  "**/*.pyc",
+  "**/*.pyo",
+
+  // other
+  "**/*.dil",
+  "**/*.ra",
+
+  // images
+  '**/*.png',
+  '**/*.jpg',
+  '**/*.jpeg',
+  '**/*.gif',
+  '**/*.ico',
+  '**/*.bmp',
+  '**/*.webp',
+  '**/*.tiff',
+  '**/*.psd',
+  '**/*.ai',
+  '**/*.ps',
+  '**/*.eps',
+
+  // fonts
+  '**/*.ttf',
+  '**/*.otf',
+  '**/*.woff',
+  '**/*.woff2',
+  '**/*.eot',
+  '**/*.ttc',
+
+  // audio
+  '**/*.mp3',
+  '**/*.wav',
+  '**/*.ogg',
+  '**/*.flac',
+  '**/*.aac',
+  '**/*.m4a',
+  '**/*.aif*',
+
+  // video
+  '**/*.mp4',
+  '**/*.mkv',
+  '**/*.avi',
+  '**/*.mov',
+  '**/*.wmv',
+  '**/*.mpg',
+  '**/*.mpeg',
+  '**/*.m2v',
+  '**/*.m4v',
+
+  // office
+  '**/*.doc',
+  '**/*.docx',
+  '**/*.docm',
+  '**/*.dot',
+  '**/*.dotx',
+  '**/*.xls',
+  '**/*.xlsx',
+
+  // documents
+  '**/*.pdf',
+  '**/*.epub',
+  '**/*.mobi',
+
+  // archives
+  '**/*.rar',
+  '**/*.zip',
+  '**/*.7z',
+  '**/*.tar',
+  '**/*.gz',
+  '**/*.bz2',
+  '**/*.bz',
+  '**/*.tbz',
+  '**/*.tgz',
 ];
 
 /**
@@ -48,6 +129,8 @@ export class LocDir {
   private cwd: string;
   private include: string[];
   private exclude: string[];
+  private analysisLanguages?: string[];
+  private allLanguages = new Languages();
 
   constructor(options: LocDirOptions) {
 
@@ -63,6 +146,7 @@ export class LocDir {
       .map(item => item.startsWith('./') ? item.substring(2) : item)
       .map(item => item.endsWith('**') ? item : `${item}/**`);
     this.cwd = options.cwd || process.cwd();
+    this.analysisLanguages = options.analysisLanguages;
   }
 
   /**
@@ -86,6 +170,7 @@ export class LocDir {
       const fullPath = slash(path.join(this.cwd, pathItem));
       if (
         !pathItem ||
+        this.ignoreLanguage(pathItem) ||
         !(await fs.pathExists(fullPath)) ||
         (await fs.stat(fullPath)).isDirectory()
       ) {
@@ -115,6 +200,14 @@ export class LocDir {
       languages,
     };
   }
+
+  /**
+   * Ignore analyzing this file if analysis languages are specified
+   * and this language is not one of them.
+   */
+  private ignoreLanguage(pathItem: string): boolean {
+    return this.analysisLanguages && !this.analysisLanguages.includes(this.allLanguages.getType(pathItem));
+  }
 }
 
 function ensureArray(arr?: string[] | string, dfault?: string) {

node_modules/github-linguist/src/file.ts

@@ -42,7 +42,7 @@ export class LocFile {
   public path: string;
   private rawPath: string;
 
-  private language = new Languages();
+  private languages = new Languages();
 
   /**
    * Creates an instance of LocFile.
@@ -52,14 +52,6 @@ export class LocFile {
     this.rawPath = rawPath;
   }
 
-  /**
-   * get file type through a path
-   */
-  private getType(path: string): string {
-    const fileExtension = `.${path.split('.').pop()}`;
-    return this.language.extensionMap[fileExtension] || '';
-  }
-
   private filterData = (data: string, regexes: Regexes): LineInfo => {
     const lines = data.split(/\n/);
     let commentLength = 0;
@@ -155,12 +147,12 @@ export class LocFile {
       newData = data || await fs.readFile(this.path, 'utf-8');
       info.name = name;
       info.size = (stat && stat.size) || 0;
-      info.languages = this.getType(this.path);
+      info.languages = this.languages.getType(this.path);
       if (!info.languages) {
         return info;
       }
       if (newData) {
-        const regexes = this.language.getRegexes(info.languages);
+        const regexes = this.languages.getRegexes(info.languages);
         info.lines = this.filterData(newData, regexes);
       }
     } catch (err) {
@@ -172,8 +164,8 @@ export class LocFile {
   public getFileInfoByContent(name: string, data: string): FileInfo {
     const info: FileInfo = Object.assign({}, DefaultFileInfo);
     info.name = name;
-    info.languages = this.getType(name);
-    info.lines = this.filterData(data, this.language.getRegexes(info.languages));
+    info.languages = this.languages.getType(name);
+    info.lines = this.filterData(data, this.languages.getRegexes(info.languages));
     return info;
   }
 }

node_modules/github-linguist/src/languages.ts

@@ -77,6 +77,14 @@ export class Languages {
   public getExtensionMap() {
     return this.extensionMap;
   }
+
+  /**
+   * get file type through a path
+   */
+   public getType(path: string): string {
+    const fileExtension = `.${path.split('.').pop()}`;
+    return this.extensionMap[fileExtension] || '';
+  }
 }
 
 export interface Regexes {