file_scanner 2.3.0 → 3.0.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 5e94d61fa43f097a1912390317cde01b2119b997
-  data.tar.gz: 12a767ee4da87adf667e5cdee448e3f473a8a233
+  metadata.gz: 28d079722f80fd8d08f242cea61b0994d6b2bb35
+  data.tar.gz: 0713446d2aa7ce967b7005aa96dcead35c3ea4e7
 SHA512:
-  metadata.gz: 526f96d30f7e39d148eaed24e90266ba44edfb1c509618691be479e66fda569e3d001903f9e05234fea0e60a4a7749b0d1bc0534fe125be9a1621357d9126388
-  data.tar.gz: 8c86dfc6a68ddd431a4656f7c833759f46717d89d8d89d967b0912de12505b562df93b3512474bbe111481c40b9eb810cf01e1f1d27b3966abb64a9617f5dc4f
+  metadata.gz: df069987cf734fe0ec58b7c857fd24524179fcac86ac5b7ab8663548bdfb6b28ad366c8182e2ed75b01c7c00735d928ebc30352b5d49e70bb509b2fa49a8fe89
+  data.tar.gz: 8dd06c2d10ae10c60a437b574431e7eb439845c1175b4e95b09370f755bfccf76dd91773001981a4950b906d98b92f02f437b6c2dbe975b613842f85cd776638

data/README.md

@@ -4,15 +4,13 @@
 * [Motivation](#motivation)
 * [Installation](#installation)
 * [Usage](#usage)
-  * [Loader](#loader)
   * [Filters](#filters)
     * [Defaults](#defaults)
     * [Custom](#custom)
   * [Worker](#worker)
-    * [Mode](#mode)
-    * [Batches](#batches)
-    * [Limit](#limit)
     * [Enumerator](#enumerator)
+    * [Block](#block)
+    * [Mode](#mode)
     * [Logger](#logger)
 
 ## Scope
@@ -39,16 +37,8 @@ gem install file_scanner
 
 ## Usage
 
-### Loader
-The first step is to create a `Loader` instance by specifying the path where the files need to be scanned with optional extensions list:
-```ruby
-require "file_scanner"
-
-loader = FileScanner::Loader.new(path: ENV["HOME"], extensions: %w[html txt])
-```
-
 ### Filters
-The second step is to provide the filters list to select file paths for which the `call` method is *truthy*.  
+The first step is to provide the filters list to select file paths for which the `call` method is *truthy*.  
 
 #### Defaults
 If you specify no filters the default ones are loaded, selecting files by:
@@ -65,51 +55,35 @@ filters = [a_week_ago, one_two_mb, hidden]
 ```
 
 #### Custom
-It is convenient to create custom filters by creating `Proc` instances that satisfy the `callable` protocol:
+It is convenient to create custom filters by using `Proc` instances that satisfy the `callable` protocol:
 ```ruby
 filters << ->(file) { File.directory?(file) }
 ```
 
 ### Worker
-Now that you have all of the collaborators in place, you can create the `Worker` instance to performs actions on the filtered paths:
-```ruby
-worker = FileScanner::Worker.new(loader: loader, filters: filters)
-worker.call do |paths|
-  # do whatever you want with the paths list
-end
-```
-
-### Mode
-By default the worker will select paths by applying any of the matching filters: this is it, it suffice just one of the specified filters to be true to grab the path.  
-In case you want restrict paths selection by all matching filters, just specify it:
-```ruby
-worker = FileScanner::Worker.new(loader: loader, filters: filters, all: true)
-```
+The second step is to create the `Worker` instance by providing the path to scan and the list of filters to apply.  
 
-#### Batches
-In case you are going to scan a large number of files, it is suggested to work in batches.  
-The `Worker` constructor accepts a `slice` attribute to give you a chance to distribute loading:
+#### Enumerator
+The `call` method of the worker return a lazy enumerator with the filtered elements, sliced by the specified number (default to 1000):
 ```ruby
-worker = FileScanner::Worker.new(loader: loader, slice: 1000)
-worker.call do |slice|
-  # perform action 1000 paths per time
-end
+worker = FileScanner::Worker.new(path: "~/Downloads", filters: filters, slice: 35)
+p worker.call
+=> #<Enumerator::Lazy: ...
 ```
 
-#### Limit
-In case you are going to apply some heavy filtering upon the selected files (i.e. reading the file in memory to get some creepy data), you can found helpful to limit the number of retuned paths before applying any filtering:
+#### Block
+To perform actions on each of the sliced paths just pass a block:
 ```ruby
-worker = FileScanner::Worker.new(loader: loader, slice: 1000, limit: 6000)
 worker.call do |slice|
-  # filters applied on a maximum of 6000 paths, working a slice of 1000 files per time
+  # perform actions on a slice of at max 35 elements
 end
 ```
 
-#### Enumerator
-In case you want access the sliced enumerator directly, just do not pass a block to the method:
+#### Mode
+By default the worker will select paths by applying any of the matching filters: this is it, it suffice just one of the specified filters to be true to grab the path.  
+In case you want restrict paths selection by all matching filters, just specify it:
 ```ruby
-slices = worker.call
-count = slices.flatten.size
+worker = FileScanner::Worker.new(loader: loader, filters: filters, all: true)
 ```
 
 #### Logger

data/file_scanner.gemspec

@@ -8,7 +8,7 @@ Gem::Specification.new do |s|
   s.version = FileScanner::VERSION
   s.authors = ["costajob"]
   s.email = ["costajob@gmail.com"]
-  s.summary = "A library to collect a set of file paths starting by a wildcard rule, filter them by any/all default/custom filters and apply a set of actions via a block call."
+  s.summary = "A library to collect a list of files by path and a set of filters, sliced by the specified value"
   s.homepage = "https://github.com/costajob/file_scanner"
   s.files = `git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(spec|test|s|features)/}) }
   s.require_paths = ["lib"]

data/lib/file_scanner/version.rb

@@ -1,3 +1,3 @@
 module FileScanner
-  VERSION = "2.3.0"
+  VERSION = "3.0.1"
 end

data/lib/file_scanner/worker.rb

@@ -1,16 +1,24 @@
+require "find"
 require "logger"
 require "file_scanner/filters"
-require "file_scanner/loader"
 
 module FileScanner
   class Worker
-    attr_reader :loader, :filters
+    SLICE = 1000
+    ALL = :all?
+    ANY = :any?
 
-    def initialize(loader:, filters: Filters::defaults, all: false, slice: nil, logger: Logger.new(nil))
-      @loader = loader
+    attr_reader :filters
+
+    def initialize(path:, 
+                   filters: Filters::defaults, 
+                   slice: SLICE, 
+                   all: false, 
+                   logger: Logger.new(nil))
+      @path = File.expand_path(path)
       @filters = filters
-      @mode = mode(all)
       @slice = slice.to_i
+      @mode = mode(all)
       @logger = logger
     end
 
@@ -24,13 +32,8 @@ module FileScanner
       raise e
     end
 
-    private def filtered
-      @loader.call.select { |file| filter(file) }
-    end
-
     private def mode(all)
-      return :all? if all
-      :any?
+      all ? ALL : ANY
     end
 
     private def filter(file)
@@ -40,8 +43,15 @@ module FileScanner
       end
     end
 
+    private def paths
+      Find.find(@path)
+    end
+
+    private def filtered
+      paths.lazy.select { |file| filter(file) }
+    end
+
     private def slices
-      return [filtered] if @slice.zero?
       filtered.each_slice(@slice)
     end
   end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: file_scanner
 version: !ruby/object:Gem::Version
-  version: 2.3.0
+  version: 3.0.1
 platform: ruby
 authors:
 - costajob
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2017-08-21 00:00:00.000000000 Z
+date: 2017-08-25 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -83,7 +83,6 @@ files:
 - file_scanner.gemspec
 - lib/file_scanner.rb
 - lib/file_scanner/filters.rb
-- lib/file_scanner/loader.rb
 - lib/file_scanner/refinements.rb
 - lib/file_scanner/version.rb
 - lib/file_scanner/worker.rb
@@ -110,6 +109,6 @@ rubyforge_project:
 rubygems_version: 2.6.8
 signing_key: 
 specification_version: 4
-summary: A library to collect a set of file paths starting by a wildcard rule, filter
-  them by any/all default/custom filters and apply a set of actions via a block call.
+summary: A library to collect a list of files by path and a set of filters, sliced
+  by the specified value
 test_files: []

data/lib/file_scanner/loader.rb

@@ -1,24 +0,0 @@
-module FileScanner
-  class Loader
-    def initialize(path:, extensions: [], limit: -1)
-      @path = File.expand_path(path)
-      @extensions = extensions
-      @limit = limit.to_i
-    end
-
-    def call
-      paths = Dir.glob(files_path)
-      return paths if @limit <= 0
-      paths.sample(@limit)
-    end
-
-    private def files_path
-      File.join(@path, "**", extensions_path)
-    end
-
-    private def extensions_path
-      return "*" if @extensions.empty?
-      "*.{#{@extensions.join(",")}}"
-    end
-  end
-end