well_read_faker 0.1.0 → 0.2.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: b242404457d34cf93e9e50e25854c0ee41129492
-  data.tar.gz: a97599aa21ff730ec81c6d9fae29641925878d43
+  metadata.gz: 72f76968ddb4ab56cddb5fa3ddaf0ef3c296e5eb
+  data.tar.gz: 05a46f05bae05e1ff7baf49820b44cb1df6a7eae
 SHA512:
-  metadata.gz: 3bc9419c52518e87897a9f644205de5fca4846d30a94a5eccbf341678ac742c09b0a91809d41ad1af16c0aa09c2ec62f39731d44bf023c99efb47bd0bd477e17
-  data.tar.gz: 47daa33cc2b6b65ceb49016f644ecac7339c550a60c17d8528ce6710a8ff11ef36a06779648118236068f1ce6676b2edf97ee7d76fce98cd19176b72d52b610e
+  metadata.gz: 54bb4b982dd7a15bdc1c986a0b1713859f6e09503bf9ef867974db2f01d6eaf42d49884c6ca23d96a9deed880de14f8f28125fd9a93a0c6c8a8f2ce6126dc271
+  data.tar.gz: 535ef04cb097a9fe9311b0d0d65cd9099240a2456386a89a4febbdea5a7988b98e22472fdc5eb2796b71c28f230a5eb23b0cc17f1b9fb144d20636c8d1ffd597

data/.gitignore

@@ -1,3 +1,5 @@
+/.ruby-gemset
+/.ruby-version
 /.bundle/
 /.yardoc
 /Gemfile.lock
@@ -7,6 +9,7 @@
 /pkg/
 /spec/reports/
 /tmp/
+*.gem
 
 # rspec failure tracking
 .rspec_status

data/.travis.yml

@@ -2,7 +2,7 @@ sudo: false
 language: ruby
 before_install: gem install bundler -v 1.14.6
 rvm:
-  - "2.4.0"
+  - "2.4.1"
   - "2.3.4"
   - "2.2.7"
   - "2.1.10"

data/README.adoc

@@ -23,7 +23,7 @@ following piece of code:
 puts WellReadFaker.paragraph
 --------------------------------------------------------------------------------
 
-Could print:
+Could print (without newlines):
 
 --------------------------------------------------------------------------------
 Thus they prayed, but not as yet would Jove grant them their prayer.
@@ -33,6 +33,43 @@ dare not with my own eyes witness this fight between my son and
 Menelaus, for Jove and the other immortals alone know which shall fall."
 --------------------------------------------------------------------------------
 
+== Custom sources
+
+Well Read Faker comes with "Iliad" bundled as a default source.  However,
+custom sources can be used:
+
+[source,ruby]
+--------------------------------------------------------------------------------
+WellReadFaker.add_source :book_in_my_language, "path/to/book", {}
+WellReadFaker[:book_in_my_language].paragraph
+WellReadFaker.default_source = :book_in_my_language
+WellReadFaker.paragraph
+WellReadFaker[:iliad].paragraph # Iliad can be still accessed
+--------------------------------------------------------------------------------
+
+The second argument passed to +WellReadFaker::add_source+ can be a string
+containing a file path, or any object which responds to +#read+, like +File+
+instance.
+
+The third argument is optional but can be used to supply additional options,
+for example to skip book descriptor or legal notes.  See
++lib/well_read_faker/load_bundled_sources.rb+ for examples.
+
+In the source text, paragraphs must be separated with blank lines.
+
+== Note about randomness quality
+
+For given text source, the paragraphs are returned in a random order, but will
+not be repeated (in the sense of +String#==+ equality) until all unique
+paragraphs from that text are returned exactly once.  After that, they are
+returned once again in the same order.
+
+Therefore it is guaranteed that if given source text contains +n+ unique
+paragraphs, then +n+ subsequent calls of +#paragraph+ method will return
+unique values.
+
+For your information, The Iliad contains over 1000 unique paragraphs.
+
 == License
 
 The gem is available as open source under the terms of the

data/lib/well_read_faker/load_bundled_sources.rb

@@ -3,6 +3,7 @@ WellReadFaker.add_source(
   File.expand_path("../../books/homer_butler_iliad.txt", __FILE__),
   begin: /The quarrel between Agamemnon/,
   end: /End of the Project Gutenberg EBook of The Iliad, by Homer/,
+  min_words: 5,
 )
 
 WellReadFaker.default_source = :iliad

data/lib/well_read_faker/source.rb

@@ -4,45 +4,83 @@ module WellReadFaker
   class Source
     include Mutex_m
 
-    attr_reader :path_to_book, :options
+    attr_reader :path_to_book_or_io, :options
 
-    def initialize path_to_book, options = {}
+    def initialize path_to_book_or_io, options = {}
       super()
-      @path_to_book = path_to_book
+      @path_to_book_or_io = path_to_book_or_io
       @options = options
     end
 
-    def text
-      mu_synchronize{ @text ||= load }
+    def paragraph
+      ensure_loaded
+      @paragraphs_arr[inc_paragraphs]
     end
 
-    def paragraph
-      text.sample
+    def ensure_loaded
+      @loaded or mu_synchronize{ @loaded or load }
     end
 
   private
 
     def load
-      raw = File.read path_to_book
-      @text = process_raw_text raw
+      if path_to_book_or_io.respond_to? :read
+        raw = path_to_book_or_io.read
+      else
+        raw = File.read path_to_book_or_io
+      end
+
+      process_raw_text raw
+      @loaded = true
     end
 
     def process_raw_text raw
-      paragraphs = raw.strip.split(/\n\s*\n/)
-      paragraphs.map!{ |m| m.gsub /\s*\n\s*/, " " }
-      while (options.key? :begin) && (paragraphs[0] !~ options[:begin])
-        paragraphs.shift or raise(
+      trimmed = trim_text_by_regexps raw, options[:begin], options[:end]
+
+      @paragraphs_arr = trimmed.split(/\n\s*\n/)
+      @paragraphs_arr.map!{ |m| m.gsub /\s*\n\s*/, " " }
+      @paragraphs_arr.uniq!
+      if options[:min_words]
+        @paragraphs_arr.select!{ |m| /(\w+\b\W*){#{options[:min_words]}}/ =~ m }
+      end
+
+      shuffle_array @paragraphs_arr
+      @paragraphs_idx = -1
+    end
+
+    def trim_text_by_regexps source_text, begin_rx, end_rx
+      retval = source_text.dup
+
+      if begin_rx
+        match_data = begin_rx.match(retval) or raise(
           ArgumentError,
-          "Regular expression #{options[:begin].inspect} not found in text."
+          "Regular expression #{begin_rx.inspect} not found in text."
         )
+        retval[0..match_data.begin(0)-1] = ""
       end
-      while (options.key? :end) && (paragraphs.pop !~ options[:end])
-        paragraphs.empty? and raise(
+
+      if end_rx
+        match_data = end_rx.match(retval) or raise(
           ArgumentError,
-          "Regular expression #{options[:end].inspect} not found in text."
+          "Regular expression #{end_rx.inspect} not found in text."
         )
+        retval[match_data.begin(0)..-1] = ""
+      end
+
+      retval.strip!
+      retval
+    end
+
+    def inc_paragraphs
+      mu_synchronize do
+        return @paragraphs_idx = (@paragraphs_idx + 1) % @paragraphs_arr.size
       end
-      paragraphs
+    end
+
+    # Extracted to a separate method to make stubbing easy (sometimes we want
+    # to preserve natural order in specs)
+    def shuffle_array array
+      array.sort_by!{ rand }
     end
 
   end

data/lib/well_read_faker/version.rb

@@ -1,3 +1,3 @@
 module WellReadFaker
-  VERSION = "0.1.0"
+  VERSION = "0.2.0"
 end

data/well_read_faker.gemspec

@@ -21,6 +21,7 @@ Gem::Specification.new do |spec|
   spec.require_paths = ["lib"]
 
   spec.add_development_dependency "bundler", "~> 1.14"
+  spec.add_development_dependency "pry"
   spec.add_development_dependency "rake", "~> 10.0"
   spec.add_development_dependency "rspec", "~> 3.5"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: well_read_faker
 version: !ruby/object:Gem::Version
-  version: 0.1.0
+  version: 0.2.0
 platform: ruby
 authors:
 - Sebastian Skałacki
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2017-04-01 00:00:00.000000000 Z
+date: 2017-06-10 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -24,6 +24,20 @@ dependencies:
     - - "~>"
       - !ruby/object:Gem::Version
         version: '1.14'
+- !ruby/object:Gem::Dependency
+  name: pry
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
 - !ruby/object:Gem::Dependency
   name: rake
   requirement: !ruby/object:Gem::Requirement
@@ -97,7 +111,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 2.6.8
+rubygems_version: 2.6.11
 signing_key: 
 specification_version: 4
 summary: Returns random fragments of Iliad or other book.