picfisher 0.2.0 → 0.2.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: d6b49dc4c4a306ff17087d90b81c875043f63062b1760eb0f481e2968b44dd66
-  data.tar.gz: 4caafb009411921cef9a4c3c60a8e231072de6a369f6b4e7a5386d636534d241
+  metadata.gz: 2b9de04d8a277e0aa73fe18b4656954e2b5990e855f6d1f566709b71ab0748e2
+  data.tar.gz: bf12cd94fb5f13307d9dd29503ba0fdc640f713ab377c024950b182521a9299d
 SHA512:
-  metadata.gz: 8cb50f69831f0421ec7cda95a942730ebdec12ceadc664a7c65fbba5322ee0c6315b5eefa06440041106756c3ba54c1fcad876c180abf551047b299da09fa2d7
-  data.tar.gz: 56739738de69a7e0f314815c0665018d516af93cc39451884ae8abe2ac1ba56db02a45cc4e272cab14a9bb32653fbd66e569bc0482999444702bb0ce9b2b8133
+  metadata.gz: d4b6edaff475b278d2c68a523a76b3301b057144de4d8b4943fe976898dc37bfe63e7dd1034ad5606022bfcbaa239801fcf9a6b7fad61de0716abc3f7bd4e1f0
+  data.tar.gz: 5ab3cd2201cf568a5836131d575c312c391ef928fbce49a26e6573b98fe4efc2b084095018aa66bd788d18aafe34749ddb287e2b4f7b1cecb063d62378449735

data/.rubocop.yml

@@ -6,3 +6,125 @@ Style/StringLiterals:
 
 Style/StringLiteralsInInterpolation:
   EnforcedStyle: double_quotes
+
+Gemspec/DateAssignment: # new in 1.10
+  Enabled: true
+Gemspec/RequireMFA: # new in 1.23
+  Enabled: true
+Layout/LineEndStringConcatenationIndentation: # new in 1.18
+  Enabled: true
+Layout/SpaceBeforeBrackets: # new in 1.7
+  Enabled: true
+Lint/AmbiguousAssignment: # new in 1.7
+  Enabled: true
+Lint/AmbiguousOperatorPrecedence: # new in 1.21
+  Enabled: true
+Lint/AmbiguousRange: # new in 1.19
+  Enabled: true
+Lint/DeprecatedConstants: # new in 1.8
+  Enabled: true
+Lint/DuplicateBranch: # new in 1.3
+  Enabled: true
+Lint/DuplicateRegexpCharacterClassElement: # new in 1.1
+  Enabled: true
+Lint/EmptyBlock: # new in 1.1
+  Enabled: true
+Lint/EmptyClass: # new in 1.3
+  Enabled: true
+Lint/EmptyInPattern: # new in 1.16
+  Enabled: true
+Lint/IncompatibleIoSelectWithFiberScheduler: # new in 1.21
+  Enabled: true
+Lint/LambdaWithoutLiteralBlock: # new in 1.8
+  Enabled: true
+Lint/NoReturnInBeginEndBlocks: # new in 1.2
+  Enabled: true
+Lint/NumberedParameterAssignment: # new in 1.9
+  Enabled: true
+Lint/OrAssignmentToConstant: # new in 1.9
+  Enabled: true
+Lint/RedundantDirGlobSort: # new in 1.8
+  Enabled: true
+Lint/RefinementImportMethods: # new in 1.27
+  Enabled: true
+Lint/RequireRelativeSelfPath: # new in 1.22
+  Enabled: true
+Lint/SymbolConversion: # new in 1.9
+  Enabled: true
+Lint/ToEnumArguments: # new in 1.1
+  Enabled: true
+Lint/TripleQuotes: # new in 1.9
+  Enabled: true
+Lint/UnexpectedBlockArity: # new in 1.5
+  Enabled: true
+Lint/UnmodifiedReduceAccumulator: # new in 1.1
+  Enabled: true
+Lint/UselessRuby2Keywords: # new in 1.23
+  Enabled: true
+Naming/BlockForwarding: # new in 1.24
+  Enabled: true
+Security/IoMethods: # new in 1.22
+  Enabled: true
+Style/ArgumentsForwarding: # new in 1.1
+  Enabled: true
+Style/CollectionCompact: # new in 1.2
+  Enabled: true
+Style/DocumentDynamicEvalDefinition: # new in 1.1
+  Enabled: true
+Style/EndlessMethod: # new in 1.8
+  Enabled: true
+Style/FileRead: # new in 1.24
+  Enabled: true
+Style/FileWrite: # new in 1.24
+  Enabled: true
+Style/HashConversion: # new in 1.10
+  Enabled: true
+Style/HashExcept: # new in 1.7
+  Enabled: true
+Style/IfWithBooleanLiteralBranches: # new in 1.9
+  Enabled: true
+Style/InPatternThen: # new in 1.16
+  Enabled: true
+Style/MapToHash: # new in 1.24
+  Enabled: true
+Style/MultilineInPatternThen: # new in 1.16
+  Enabled: true
+Style/NegatedIfElseCondition: # new in 1.2
+  Enabled: true
+Style/NestedFileDirname: # new in 1.26
+  Enabled: true
+Style/NilLambda: # new in 1.3
+  Enabled: true
+Style/NumberedParameters: # new in 1.22
+  Enabled: true
+Style/NumberedParametersLimit: # new in 1.22
+  Enabled: true
+Style/OpenStructUse: # new in 1.23
+  Enabled: true
+Style/QuotedSymbols: # new in 1.16
+  Enabled: true
+Style/RedundantArgument: # new in 1.4
+  Enabled: true
+Style/RedundantInitialize: # new in 1.27
+  Enabled: true
+Style/RedundantSelfAssignmentBranch: # new in 1.19
+  Enabled: true
+Style/SelectByRegexp: # new in 1.22
+  Enabled: true
+Style/StringChars: # new in 1.12
+  Enabled: true
+Style/SwapValues: # new in 1.1
+  Enabled: true
+
+Metrics/MethodLength:
+  Max: 15
+  Exclude:
+    - 'test/**/*'
+
+Metrics/AbcSize:
+  Exclude:
+    - 'test/**/*'
+
+Layout/LineLength:
+  Exclude:
+    - 'test/**/*'

data/CHANGELOG.md

@@ -5,6 +5,29 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [0.2.1] - 2024-05-30
+
+### Fixed
+
+- Removed development gems from production dependencies
+
+
+## [0.2.1] - 2024-05-30
+
+### Added
+
+- Show running version in the first log message
+
+### Changed
+
+- Rubocop cops application
+- Update TODO.md
+
+### Fixed
+
+- Removed outdated comment
+
+
 ## [0.2.0] - 2024-05-30
 
 ### Added

data/README.md

@@ -12,7 +12,7 @@ gem install picfisher
 ## Usage
 
 ```
-picfisher [images_file_path] [output_directory_path]
+picfisher <images_file_path> <output_directory_path>
 ```
 
 For example:

data/REQUIREMENTS.md

@@ -0,0 +1,27 @@
+# Getsafe Backend Coding Challenge
+
+## Task context
+Imagine you are employed at a hypothetical company called “The Big Picture Corp” where the product department is requesting a tool to download a list of images from a plain text file. For now there are not many requirements from product yet and you only know that they want a simple command line tool for downloading images from a list of urls and storing them on the local harddrive. From the product vision however, it’s already clear that having the functionality of batch downloading images will be important to the product and is likely to be used in several different contexts.
+
+## Assignment
+Implement the functionality of downloading images from a given plain text file. Document your solution in this github repository and quickly explain why you think this is a good solution to the given task.
+
+## Some things to keep in mind
+- We prefer if you use Ruby, but we’re ok if you use a different language
+- You can assume that the image urls in a given file are separated by whitespace and can potentially include invalid urls
+- Your code should be executable through a command line interface (script, rake task, ...)
+- You can assume your code will be used in production and will also be further developed by other developers over time - therefore make decision accordingly
+- Try to keep your commits history well organised and clean, like you would do in a pull request for a real task assignment.
+
+## What we pay attention to
+1. Does your solution work?
+2. Is the code clear and maintainable?
+3. Is the code tested?
+4. Is your solution documented?
+5. Have all instructions been followed?
+
+Bonus: Document your thought process.
+
+We're here for you in case you have any questions!
+
+## Above all: have fun!✌🏻

data/TODO.md

@@ -1,8 +1,10 @@
 # TODO
 
-- Create the output directory if it doesn't exist. Or add a parameter to allow the user to decide this.
+- If the output directory doesn't exist, create it. We can also add a parameter to allow the user to decide on this.
 - Check if the Downloader is going to overwrite a file that already exists. Add an option to `force` if not stop with an error.
 - Add a progress bar for the downloading phase.
 - Allow multiple concurrent downloads. Add an extra param to decide the number, default `5`
-- Add error handling to the Downloader. Many things can be wrong when connecting to the internet.
-- Allow URLs without image extension. This requires the source urls file to have a predictable estructure. Or we request all the images and check the media type of the response.
+✔ Add error handling to the Downloader. Many things can be wrong when connecting to the internet.
+- Allow URLs without image extension. This requires the URLs' source file to have a predictable structure. Or we request all the images and check the media type of the response.
+- If we pass an URL instead of a file path, the script will detect it, download the URL, and extract the images from there.
+- Pass Rubocop cops

data/exe/picfisher

@@ -1,7 +1,6 @@
 #!/usr/bin/env ruby
 # frozen_string_literal: true
 
-require "bundler/setup"
 require "picfisher"
 
 PicFisher.fish(ARGV[0], ARGV[1])

data/lib/picfisher/downloader.rb

@@ -1,8 +1,18 @@
+# frozen_string_literal: true
+
 require "open-uri"
 
 module PicFisher
+  # Downloads an image from an URL
   module Downloader
-    # TODO: We need to add error handling here
+    # Downloads an image from an URL
+    # @param url [String]
+    # @param output_path [String]
+    # @return [nil]
+    # @raise [PicFisher::Error]
+    # @example
+    #   PicFisher::Downloader.download("https://example.com/image_in_internet.png", "OUTPUT_PATH")
+    #   PicFisher::Downloader.download("https://example.com/not_existing.png", "OUTPUT_PATH")
     def self.download(url, output_path)
       PicFisher::Log.debug("Fishing #{url} to #{output_path}")
 
@@ -11,18 +21,16 @@ module PicFisher
       rescue OpenURI::HTTPError => e
         message = "Failed to fish #{url}: #{e}"
         PicFisher::Log.error(message)
-        raise PicFisher::Error.new(message)
+        raise PicFisher::Error, message
       end
     end
 
-    private
-
     def self._dowload(url, output_path)
-      io_stream = OpenURI::open_uri(url)
+      io_stream = OpenURI.open_uri(url)
 
-      File.open(output_path, "wb") do |f|
-        f.write(io_stream.read)
-      end
+      File.binwrite(output_path, io_stream.read)
     end
+
+    private_class_method :_dowload
   end
 end

data/lib/picfisher/fishing_boat.rb

@@ -1,6 +1,15 @@
+# frozen_string_literal: true
+
 module PicFisher
+  # Extracts the image urls from the given file and download them to the given directory
   module FishingBoat
-    # REVIEW: we could use keyword params if we see it adds readability
+    # Extracts the image urls from the given file and download them to the given directory
+    # @param images_file_path [String]
+    # @param output_directory_path [String]
+    # @return [nil]
+    # @raise [PicFisher::Error]
+    # @example
+    #   PicFisher::FishingBoat.fish("images.txt","~/Downloads/fished_images")
     def self.fish(images_file_path, output_directory_path)
       PicFisher::Log.info("Fishing from #{images_file_path} to #{output_directory_path}")
 

data/lib/picfisher/log.rb

@@ -1,25 +1,26 @@
+# frozen_string_literal: true
+
 module PicFisher
+  # Print a message to the console
+  # @param debug_level [Symbol]
+  # @return [nil]
+  # @example
+  #   PicFisher::Log.debug("message")
+  #   PicFisher::Log.info("message")
+  #   PicFisher::Log.error("message")
   module Log
     def self.debug(message)
-      if ["debug"].include? debug_level
-        output(:debug, message)
-      end
+      output(:debug, message) if ["debug"].include? debug_level
     end
 
     def self.info(message)
-      if ["debug", "info"].include? debug_level
-        output(:info, message)
-      end
+      output(:info, message) if %w[debug info].include? debug_level
     end
 
     def self.error(message)
-      if ["debug", "info", "error"].include? debug_level
-        output(:error, message)
-      end
+      output(:error, message) if %w[debug info error].include? debug_level
     end
 
-    private
-
     def self.output(level, message)
       final_message = "PicFisher [#{level.upcase}] #{message}"
       Kernel.puts(final_message)
@@ -28,5 +29,7 @@ module PicFisher
     def self.debug_level
       ENV["DEBUG_LEVEL"] || "info" # default is info
     end
+
+    private_class_method :debug_level
   end
 end

data/lib/picfisher/sanitizer.rb

@@ -1,19 +1,25 @@
+# frozen_string_literal: true
+
 module PicFisher
+  # Sanitizes an image url
   module Sanitizer
+    # Sanitizes an image url
+    # @param url [String]
+    # @return [String]
+    # @example
+    #   PicFisher::Sanitizer.sanitize_image_url("https://example.com/image_in_internet.png")
     def self.sanitize_image_url(url)
       filename_extension = File.extname(url)
       filename_extension_escaped = Regexp.escape(filename_extension) # to escape the dot "."
       result =
         url
-          .sub(/#{filename_extension_escaped}$/, "")
-          .gsub(/[^\w\s-]+/, "_")
-          .gsub(/(^|\b\s)\s+($|\s?\b)/, "\\1\\2")
-          .gsub(/\s+/, "_")
+        .sub(/#{filename_extension_escaped}$/, "")
+        .gsub(/[^\w\s-]+/, "_")
+        .gsub(/(^|\b\s)\s+($|\s?\b)/, "\\1\\2")
+        .gsub(/\s+/, "_")
 
       result = "#{result}#{filename_extension}"
-
       PicFisher::Log.debug("Sanitizing url '#{url}': #{result}")
-
       result
     end
   end

data/lib/picfisher/url_extractor.rb

@@ -1,17 +1,26 @@
+# frozen_string_literal: true
+
 require "uri"
 
 module PicFisher
+  # Extracts image urls from a string
   module URLExtractor
     # NOTE: using URI.regexp(["http", "https"]) didn't work for me
-    URL_REGEX = /https?:\/\/[^\s,]+/
-    IMAGE_EXTENSITONS = %w(.jpg .jpeg .png .gif .webp .bmp .ico .svg .tiff or .tif .psd .raw .cr2 .nrw .arw .dng .nef .orf .sr2 .raf .tif .tiff .djvu)
+    URL_REGEX = %r{https?://[^\s,]+}
+    IMAGE_EXTENSITONS = %w[.jpg .jpeg .png .gif .webp .bmp .ico .svg .tiff or .tif .psd .raw .cr2 .nrw .arw .dng .nef
+                           .orf .sr2 .raf .tif .tiff .djvu].freeze
 
+    # Extracts image urls from a string
+    # @param string [String]
+    # @return [Array<String>]
+    # @example
+    #   PicFisher::URLExtractor.extract("https://example.com/image_in_internet.png, https://example.com/another.png")
     def self.extract(string)
       result =
         string
-          .scan(URL_REGEX)
-          .select { |url| url.end_with?(*IMAGE_EXTENSITONS) }
-          .uniq
+        .scan(URL_REGEX)
+        .select { |url| url.end_with?(*IMAGE_EXTENSITONS) }
+        .uniq
 
       PicFisher::Log.debug("Extracted urls: #{result.join("|")}")
 

data/lib/picfisher/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module PicFisher
-  VERSION = "0.2.0"
+  VERSION = "0.2.3"
 end

data/lib/picfisher.rb

@@ -7,32 +7,59 @@ require_relative "picfisher/downloader"
 require_relative "picfisher/fishing_boat"
 require_relative "picfisher/log"
 
+# Extracts the image urls from the given file and download them to the given directory
 module PicFisher
   class Error < StandardError; end
 
-  # REVIEW: we could use keyword params if we see it adds readability
+  # Extracts the image urls from the given file and download them to the given directory
+  # @param images_file_path [String]
+  # @param output_directory_path [String]
+  # @return [nil]
+  # @raise [PicFisher::Error]
+  # @example
+  #   PicFisher.fish("images.txt","~/Downloads/fished_images")
   def self.fish(images_file_path, output_directory_path)
-    PicFisher::Log.info "PicFisher is running..."
+    PicFisher::Log.info "PicFisher [#{PicFisher::VERSION}] is running..."
 
-    if images_file_path.nil? || output_directory_path.nil?
-      message = "Use: picfisher [images_file_path] [output_directory_path]"
-      PicFisher::Log.error(message)
-      raise PicFisher::Error.new(message)
+    run_validations(images_file_path, output_directory_path)
+
+    PicFisher::FishingBoat.fish(images_file_path, output_directory_path)
+    PicFisher::Log.info "PicFisher is finished!"
+  end
+
+  class << self
+    private
+
+    def run_validations(images_file_path, output_directory_path)
+      validate_paths(images_file_path, output_directory_path)
+      validate_origin_exists(images_file_path)
+      validate_output_exists(output_directory_path)
     end
 
-    if !File.exist?(images_file_path)
-      message = "File not found: #{images_file_path}"
-      PicFisher::Log.error(message)
-      raise PicFisher::Error.new(message)
+    # rubocop:disable Style/GuardClause
+    def validate_paths(images_file_path, output_directory_path)
+      if images_file_path.nil? || output_directory_path.nil?
+        message = "Use: picfisher <images_file_path> <output_directory_path>"
+        PicFisher::Log.error(message)
+        raise PicFisher::Error, message
+      end
     end
 
-    if !Dir.exist?(output_directory_path)
-      message = "Directory not found: #{output_directory_path}"
-      PicFisher::Log.error(message)
-      raise PicFisher::Error.new(message)
+    def validate_origin_exists(images_file_path)
+      unless File.exist?(images_file_path)
+        message = "File not found: #{images_file_path}"
+        PicFisher::Log.error(message)
+        raise PicFisher::Error, message
+      end
     end
 
-    PicFisher::FishingBoat.fish(images_file_path, output_directory_path)
-    PicFisher::Log.info "PicFisher is finished!"
+    def validate_output_exists(output_directory_path)
+      unless Dir.exist?(output_directory_path)
+        message = "Directory not found: #{output_directory_path}"
+        PicFisher::Log.error(message)
+        raise PicFisher::Error, message
+      end
+    end
+    # rubocop:enable Style/GuardClause
   end
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: picfisher
 version: !ruby/object:Gem::Version
-  version: 0.2.0
+  version: 0.2.3
 platform: ruby
 authors:
 - Fernando Guillen
@@ -10,6 +10,20 @@ bindir: exe
 cert_chain: []
 date: 2024-05-30 00:00:00.000000000 Z
 dependencies:
+- !ruby/object:Gem::Dependency
+  name: minitest
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '5.16'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '5.16'
 - !ruby/object:Gem::Dependency
   name: open-uri
   requirement: !ruby/object:Gem::Requirement
@@ -39,33 +53,33 @@ dependencies:
       - !ruby/object:Gem::Version
         version: 0.13.0
 - !ruby/object:Gem::Dependency
-  name: rake
+  name: mocha
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '13.0'
-  type: :runtime
+        version: '2.3'
+  type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '13.0'
+        version: '2.3'
 - !ruby/object:Gem::Dependency
-  name: minitest
+  name: rake
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '5.16'
-  type: :runtime
+        version: '13.0'
+  type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '5.16'
+        version: '13.0'
 - !ruby/object:Gem::Dependency
   name: rubocop
   requirement: !ruby/object:Gem::Requirement
@@ -73,7 +87,7 @@ dependencies:
     - - "~>"
       - !ruby/object:Gem::Version
         version: '1.21'
-  type: :runtime
+  type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
@@ -100,20 +114,6 @@ dependencies:
     - - ">="
       - !ruby/object:Gem::Version
         version: 3.23.1
-- !ruby/object:Gem::Dependency
-  name: mocha
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '2.3'
-  type: :development
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '2.3'
 description: Reading all the image URLs from a given text file and download them to
   a given directory.
 email:
@@ -127,6 +127,7 @@ files:
 - CHANGELOG.md
 - LICENSE.txt
 - README.md
+- REQUIREMENTS.md
 - Rakefile
 - TODO.md
 - exe/picfisher
@@ -145,6 +146,7 @@ metadata:
   homepage_uri: https://github.com/fguillen/PicFisher
   source_code_uri: https://github.com/fguillen/PicFisher
   changelog_uri: https://github.com/fguillen/PicFisher/blob/main/CHANGELOG.md
+  rubygems_mfa_required: 'true'
 post_install_message:
 rdoc_options: []
 require_paths: