FEAT: Add an option to not prune non visited keys. Closes #2

README.md

@@ -1,5 +1,5 @@
 # file-entry-cache
-> Super simple cache for file metadata, useful for process that work o a given series of files 
+> Super simple cache for file metadata, useful for process that work o a given series of files
 > and that only need to repeat the job on the changed ones since the previous run of the process — Edit
 
 [![NPM Version](http://img.shields.io/npm/v/file-entry-cache.svg?style=flat)](https://npmjs.org/package/file-entry-cache)
@@ -14,7 +14,7 @@ npm i --save file-entry-cache
 ## Usage
 
 ```js
-// loads the cache, if one does not exists for the given 
+// loads the cache, if one does not exists for the given
 // Id a new one will be prepared to be created
 var fileEntryCache = require('file-entry-cache');
 
@@ -25,18 +25,23 @@ var files = expand('../fixtures/*.txt');
 // the first time this method is called, will return all the files
 var oFiles = cache.getUpdatedFiles(files);
 
-// this will persist this to disk checking each file stats and 
+// this will persist this to disk checking each file stats and
 // updating the meta attributes `size` and `mtime`.
 // custom fields could also be added to the meta object and will be persisted
 // in order to retrieve them later
-cache.reconcile(); 
+cache.reconcile();
+
+// use this if you want the non visited file entries to be kept in the cache
+// for more than one execution
+//
+// cache.reconcile( true /* noPrune */)
 
 // on a second run
 var cache2 = fileEntryCache.create('testCache');
 
 // will return now only the files that were modified or none
 // if no files were modified previous to the execution of this function
-var oFiles = cache.getUpdatedFiles(files);  
+var oFiles = cache.getUpdatedFiles(files);
 
 // if you want to prevent a file from being considered non modified
 // something useful if a file failed some sort of validation
@@ -64,32 +69,38 @@ entry = {
 
 ## Motivation for this module
 
-I needed a super simple and dumb **in-memory cache** with optional disk persistence (write-back cache) in order to make 
+I needed a super simple and dumb **in-memory cache** with optional disk persistence (write-back cache) in order to make
 a script that will beautify files with `esformatter` to execute only on the files that were changed since the last run.
 
 In doing so the process of beautifying files was reduced from several seconds to a small fraction of a second.
 
-This module uses [flat-cache](https://www.npmjs.com/package/flat-cache) a super simple `key/value` cache storage with 
+This module uses [flat-cache](https://www.npmjs.com/package/flat-cache) a super simple `key/value` cache storage with
 optional file persistance.
 
-The main idea is to read the files when the task begins, apply the transforms required, and if the process succeed, 
-then store the new state of the files. The next time this module request for `getChangedFiles` will return only 
+The main idea is to read the files when the task begins, apply the transforms required, and if the process succeed,
+then store the new state of the files. The next time this module request for `getChangedFiles` will return only
 the files that were modified. Making the process to end faster.
 
 This module could also be used by processes that modify the files applying a transform, in that case the result of the
-transform could be stored in the `meta` field, of the entries. Anything added to the meta field will be persisted. 
-Those processes won't need to call `getChangedFiles` they will instead call `normalizeEntries` that will return the 
+transform could be stored in the `meta` field, of the entries. Anything added to the meta field will be persisted.
+Those processes won't need to call `getChangedFiles` they will instead call `normalizeEntries` that will return the
 entries with a `changed` field that can be used to determine if the file was changed or not. If it was not changed
 the transformed stored data could be used instead of actually applying the transformation, saving time in case of only
 a few files changed.
 
 In the worst case scenario all the files will be processed. In the best case scenario only a few of them will be processed.
 
 ## Important notes
-- The values set on the meta attribute of the entries should be `stringify-able` ones, meaning no circular references
-- All the changes to the cache state are done to memory first and only persisted after reconcile
+- The values set on the meta attribute of the entries should be `stringify-able` ones if possible, flat-cache uses `circular-json` to try to persist circular structures, but this should be considered experimental. The best results are always obtained with non circular values
+- All the changes to the cache state are done to memory first and only persisted after reconcile.
+- By default non visited entries are removed from the cache. This is done to prevent the file from growing too much. If this is not an issue and
+  you prefer to do a manual pruning of the cache files, you can pass `true` to the `reconcile` call. Like this:
+
+  ```javascript
+  cache.reconcile( true /* noPrune */ );
+  ```
 
-## License 
+## License
 
 MIT
 

cache.js

@@ -16,7 +16,7 @@ module.exports = {
 
     return {
       /**
-       * the flat cache storage used to persist the metadata of the files
+       * the flat cache storage used to persist the metadata of the `files
        * @type {Object}
        */
       cache: cache,
@@ -161,16 +161,18 @@ module.exports = {
       },
       /**
        * Sync the files and persist them to the cache
-       *
+       * @param [noPrune=false] {Boolean} whether to remove non visited/saved entries
        * @method reconcile
        */
-      reconcile: function () {
+      reconcile: function ( noPrune ) {
         var entries = normalizedEntries;
 
         var keys = Object.keys( entries );
+
         if ( keys.length === 0 ) {
           return;
         }
+
         keys.forEach( function ( entryName ) {
           var cacheEntry = entries[ entryName ];
           var stat = fs.statSync( cacheEntry.key );
@@ -183,7 +185,7 @@ module.exports = {
           cache.setKey( entryName, meta );
         } );
 
-        cache.save();
+        cache.save( noPrune );
       }
     };
   }

package.json

@@ -16,20 +16,20 @@
     "node": ">=0.10.0"
   },
   "scripts": {
-    "beautify": "esbeautifier 'cache.js' 'specs/**/*.js'",
-    "beautify-check": "esbeautifier -k 'cache.js' 'specs/**/*.js'",
+    "beautify": "esbeautifier 'cache.js' 'test/**/*.js'",
+    "beautify-check": "npm run beautify -- -k",
     "eslint": "eslinter 'cache.js' 'specs/**/*.js'",
     "lint": "npm run beautify && npm run eslint",
     "verify": "npm run beautify-check && npm run eslint",
     "install-hooks": "prepush install && changelogx install-hook && precommit install",
     "changelog": "changelogx -f markdown -o ./changelog.md",
     "do-changelog": "npm run changelog && git add ./changelog.md && git commit -m 'DOC: Generate changelog' --no-verify",
-    "pre-v": "npm run verify",
+    "pre-v": "npm run test",
     "post-v": "npm run do-changelog && git push --no-verify && git push --tags --no-verify",
     "bump-major": "npm run pre-v && npm version major -m 'BLD: Release v%s' && npm run post-v",
     "bump-minor": "npm run pre-v && npm version minor -m 'BLD: Release v%s' && npm run post-v",
     "bump-patch": "npm run pre-v && npm version patch -m 'BLD: Release v%s' && npm run post-v",
-    "test": "mocha -R spec test/specs",
+    "test": "npm run verify && mocha -R spec test/specs",
     "cover": "istanbul cover test/runner.js html text-summary",
     "watch": "watch-run -i -p 'test/specs/**/*.js' istanbul cover test/runner.js html text-summary"
   },
@@ -72,14 +72,13 @@
     "precommit": "^1.1.5",
     "prepush": "^3.1.4",
     "proxyquire": "^1.3.1",
-    "read-file": "^0.2.0",
     "sinon": "^1.12.2",
     "sinon-chai": "^2.7.0",
     "watch-run": "^1.2.1",
-    "write": "^0.2.1"
+    "write": "^0.3.1"
   },
   "dependencies": {
-    "flat-cache": "^1.0.9",
+    "flat-cache": "^1.2.1",
     "object-assign": "^4.0.1"
   }
 }

test/runner.js

@@ -1,44 +1,40 @@
-"use strict";
-
 // we run mocha manually otherwise istanbul coverage won't work
 // run `npm test --coverage` to generate coverage report
 
-var Mocha = require('mocha');
-
-
-// ---
-
+var Mocha = require( 'mocha' );
 
 
 // to set these options run the test script like:
 //  > BAIL=true GREP=array_expression REPORTER=dot npm test
 var opts = {
   ui: 'bdd',
   bail: !!(process.env.BAIL),
-  reporter:( process.env.REPORTER || 'spec'),
+  reporter: (process.env.REPORTER || 'spec'),
   grep: process.env.GREP,
   colors: true
 };
 
 // we use the dot reporter on travis since it works better
-if (process.env.TRAVIS) {
+if ( process.env.TRAVIS ) {
   opts.reporter = 'dot';
 }
 
-var m = new Mocha(opts);
+var m = new Mocha( opts );
 
-if (process.env.INVERT) {
+if ( process.env.INVERT ) {
   m.invert();
 }
 
-var expand = require('glob-expand');
-expand('test/specs/**/*.js').forEach(function (file){
-  m.addFile(file);
-});
+var expand = require( 'glob-expand' );
+expand( 'test/specs/**/*.js' ).forEach( function ( file ) {
+  m.addFile( file );
+} );
 
-m.run(function(err) {
+m.run( function ( err ) {
   var exitCode = err ? 1 : 0;
-  if (err) console.log('failed tests: ' + err);
-  process.exit(exitCode);
-});
+  if ( err ) {
+    console.log( 'failed tests: ' + err );
+  }
 
+  process.exit( exitCode ); // eslint-disable-line
+} );

test/specs/cache.js

@@ -3,14 +3,13 @@ describe( 'file-entry-cache', function () {
   var expect = require( 'chai' ).expect;
   var path = require( 'path' );
   var write = require( 'write' ).sync;
-  var read = require( 'read-file' ).readFileSync;
   var fileEntryCache = require( '../../cache' );
 
   function expand() {
-    return require( 'glob-expand' ).apply(null, arguments).map(function (file) {
-      return file.split('/').join(path.sep);
-    });
-  };
+    return require( 'glob-expand' ).apply( null, arguments ).map( function ( file ) {
+      return file.split( '/' ).join( path.sep );
+    } );
+  }
 
   var fixturesDir = path.resolve( __dirname, '../fixtures' );
   var del = require( 'del' ).sync;
@@ -37,9 +36,7 @@ describe( 'file-entry-cache', function () {
   var cache;
 
   var delCacheAndFiles = function () {
-    del( fixturesDir, {
-      force: true
-    } );
+    del( fixturesDir, { force: true } );
     cache && cache.deleteCacheFile();
   };
 
@@ -80,8 +77,6 @@ describe( 'file-entry-cache', function () {
 
       cache.reconcile();
 
-      //write( file, 'some different content');
-
       expect( cache.hasFileChanged( file ) ).to.be.false;
 
     } );
@@ -128,7 +123,7 @@ describe( 'file-entry-cache', function () {
     cache.reconcile();
 
     oFiles = cache.getUpdatedFiles( files );
-    expect( oFiles ).to.deep.equal( [] );
+    expect( oFiles ).to.deep.equal( [ ] );
 
     cache.deleteCacheFile();
 
@@ -191,7 +186,7 @@ describe( 'file-entry-cache', function () {
     cache = fileEntryCache.create( 'testCache2' );
     var files = cache.getUpdatedFiles( null );
     cache.reconcile();
-    expect( files ).to.deep.equal( [] );
+    expect( files ).to.deep.equal( [ ] );
   } );
 
   it( 'should not fail if calling reconcile without a prior call to `getChangedFiles` or `normalizeEntries`', function () {
@@ -216,6 +211,62 @@ describe( 'file-entry-cache', function () {
 
     } );
 
+    it( 'should remove non visited entries from the cache', function () {
+      cache = fileEntryCache.create( 'testCache' );
+
+      var files = expand( path.resolve( __dirname, '../fixtures/*.txt' ) );
+      cache.normalizeEntries( files );
+
+      cache.reconcile();
+
+      // the f2.txt file is in the cache
+      expect( cache.cache.getKey( path.resolve( __dirname, '../fixtures/f2.txt' ) ) ).to.not.equal( undefined );
+
+      // load the cache again
+      cache = fileEntryCache.create( 'testCache' );
+
+      // when recently loaded all entries are in the cache
+      expect( cache.cache.keys().length ).to.equal( 4 );
+
+      // we check only one file
+      expect( cache.hasFileChanged( path.resolve( __dirname, '../fixtures/f4.txt' ) ) ).to.be.false;
+
+      cache.reconcile();
+
+      // after reconcile we will only have 1 key because we just visited one entry
+      expect( cache.cache.getKey( path.resolve( __dirname, '../fixtures/f2.txt' ) ) ).to.equal( undefined );
+      expect( cache.cache.keys().length ).to.equal( 1 );
+
+    } );
+
+    it( 'should not remove visited entries from the cache if reconcile is called with noPrune=true', function () {
+      cache = fileEntryCache.create( 'testCache' );
+
+      var files = expand( path.resolve( __dirname, '../fixtures/*.txt' ) );
+      cache.normalizeEntries( files );
+
+      cache.reconcile();
+
+      // the f2.txt file is in the cache
+      expect( cache.cache.getKey( path.resolve( __dirname, '../fixtures/f2.txt' ) ) ).to.not.equal( undefined );
+
+      // load the cache again
+      cache = fileEntryCache.create( 'testCache' );
+
+      // when recently loaded all entries are in the cache
+      expect( cache.cache.keys().length ).to.equal( 4 );
+
+      // we check only one file
+      expect( cache.hasFileChanged( path.resolve( __dirname, '../fixtures/f4.txt' ) ) ).to.be.false;
+
+      cache.reconcile( true );
+
+      // after reconcile we will only have 1 key because we just visited one entry
+      expect( cache.cache.getKey( path.resolve( __dirname, '../fixtures/f2.txt' ) ) ).to.not.equal( undefined );
+      expect( cache.cache.keys().length ).to.equal( 4 );
+
+    } );
+
     it( 'should return fileDescriptor for all the passed files', function () {
       cache = fileEntryCache.create( 'testCache' );
 
@@ -241,7 +292,7 @@ describe( 'file-entry-cache', function () {
     it( 'should not fail if a null array of files is passed', function () {
       cache = fileEntryCache.create( 'testCache' );
       var oFiles = cache.normalizeEntries( null );
-      expect( oFiles ).to.deep.equal( [] );
+      expect( oFiles ).to.deep.equal( [ ] );
     } );
 
   } );
@@ -258,9 +309,7 @@ describe( 'file-entry-cache', function () {
       var files = expand( path.resolve( __dirname, '../fixtures/*.txt' ) );
       var entries = cache.normalizeEntries( files );
 
-      entries[ 1 ].meta.data = {
-        foo: 'bar'
-      };
+      entries[ 1 ].meta.data = { foo: 'bar' };
       entries[ 2 ].meta.data = {
         baz: {
           some: 'foo'