file_scanner 2.0.4 → 2.1.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: b8d05591c33d88bc64ed6029b3dba902b3b61bdd
-  data.tar.gz: d635fe64822621e9a071759e7f1b7a254240555b
+  metadata.gz: b97bb23d5031571dadb1bbc7d3230fc6d05a1973
+  data.tar.gz: 0d042f4d231a4aa1e8f462cdc7cbd3c523bc313f
 SHA512:
-  metadata.gz: 7d1c93540a329ab31185695f9632e398f05420da233898119586c908da20771f351d5f431da61b4e6fc13468d5db22f724c092a4407c8639a0bc205f738e0217
-  data.tar.gz: e8b662063dc934a7b699f875f33f251901d62bdbb38ae44453c471fb5f29c62f3d1545fd7c659c8d1728e857b194bff63b25c61389b13d334c946a0b58982560
+  metadata.gz: a3fc550fd7fcf6f346b8fec40942dca5049f1fa1b00a24e696dcf38bffff3d7960cd5f17594482acb61ea932e3caae24c89b0c9eb54d3f82cac2612b75b0d2f2
+  data.tar.gz: ba4bc0f86eee6d8997e053ca0d00f5d58fa93f76a4d5f043728924630f53a8ea75261bc9ce696d4f2bef441e649a5e9ac98211ef9cd8e374a2f434d499f1fc5d

data/README.md

@@ -9,7 +9,9 @@
     * [Defaults](#defaults)
     * [Custom](#custom)
   * [Worker](#worker)
+    * [Mode](#mode)
     * [Batches](#batches)
+    * [Limit](#limit)
     * [Enumerator](#enumerator)
     * [Logger](#logger)
     * [Factory](#factory)
@@ -48,7 +50,6 @@ 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*.  
-Selection is done with the `any?` predicate, so also one matching filter will do the selection.
 
 #### Defaults
 If you specify no filters the default ones are loaded, selecting files by:
@@ -79,6 +80,13 @@ worker.call do |paths|
 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)
+```
+
 #### 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:
@@ -89,6 +97,15 @@ worker.call do |slice|
 end
 ```
 
+#### Limit
+In case you are still concerned about the selected paths number, you can limit it before applying the slicing (if any):
+```ruby
+worker = FileScanner::Worker.new(loader: loader, slice: 1000, limit: 7500)
+worker.call do |slice|
+  # perform action 1000 paths per time till reaching the specified limit
+end
+```
+
 #### Enumerator
 In case you want access the sliced enumerator directly, just do not pass a block to the method:
 ```ruby
@@ -119,8 +136,8 @@ end
 #### Factory
 You can create loader and worker instances at once by using the available factory:
 ```ruby
-worker = FileScanner::Worker.factory(path: ENV["HOME"], extensions: %w[html txt], filters: filters, logger: my_logger, slice: 1000)
+worker = FileScanner::Worker.factory(path: ENV["HOME"], extensions: %w[html txt], filters: filters, all: true, slice: 1000, limit: 7500, logger: my_logger)
 worker.call do |slice, logger|
-  # perform action 1000 paths per time
+  # perform action 1000 paths per time till reaching the specified limit
 end
 ```

data/lib/file_scanner/version.rb

@@ -1,3 +1,3 @@
 module FileScanner
-  VERSION = "2.0.4"
+  VERSION = "2.1.0"
 end

data/lib/file_scanner/worker.rb

@@ -4,23 +4,19 @@ require "file_scanner/loader"
 
 module FileScanner
   class Worker
-    def self.default_logger
-      Logger.new(nil).tap do |logger|
-        logger.level = Logger::ERROR
-      end
-    end
-
-    def self.factory(path:, extensions: [], filters: [], logger: default_logger, slice: nil)
+    def self.factory(path:, extensions: [], filters: [], all: false, slice: nil, limit: -1, logger: Logger.new(nil))
       loader = Loader.new(path: path, extensions: extensions)
-      new(loader: loader, filters: filters, logger: logger, slice: slice)
+      new(loader: loader, filters: filters,  slice: slice, all: all, limit: limit, logger: logger)
     end
 
     attr_reader :loader, :filters
 
-    def initialize(loader:, filters: Filters::defaults, logger: self.class.default_logger, slice: nil)
+    def initialize(loader:, filters: Filters::defaults, all: false, slice: nil, limit: -1, logger: Logger.new(nil))
       @loader = loader
       @filters = filters
+      @all = !!all
       @slice = slice.to_i
+      @limit = limit.to_i
       @logger = logger
     end
 
@@ -34,21 +30,36 @@ module FileScanner
       raise e
     end
 
+    private def fetch_mode(mode)
+      return :any? unless @filters.respond_to?(mode)
+      mode
+    end
+
     private def files
       paths = @loader.call
       paths.select! { |file| filter(file) } || paths
     end
 
+    private def limit
+      return files if @limit <= 0
+      files.first(@limit)
+    end
+
+    private def mode
+      return :all? if @all
+      :any?
+    end
+
     private def filter(file)
-      @filters.any? do |filter|
-        @logger.debug { "applying \e[33m#{filter}\e[0m to #{File.basename(file)}" }
+      @filters.send(mode) do |filter|
+        @logger.debug { "selecting by \e[33m#{mode}\e[0m with filter \e[33m#{filter}\e[0m on #{File.basename(file)}" }
         filter.call(file)
       end
     end
 
     private def slices
-      return [files] if @slice.zero?
-      files.each_slice(@slice)
+      return [limit] if @slice.zero?
+      limit.each_slice(@slice)
     end
   end
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: file_scanner
 version: !ruby/object:Gem::Version
-  version: 2.0.4
+  version: 2.1.0
 platform: ruby
 authors:
 - costajob
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2017-08-11 00:00:00.000000000 Z
+date: 2017-08-16 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler