format_parser 0.9.4 → 0.10.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
-SHA1:
-  metadata.gz: 1ea761c606eb23bb10fd39f158afa2a628930018
-  data.tar.gz: eda078a306d8ded4dbdbdb4570608fe99b80b3e8
+SHA256:
+  metadata.gz: d4253990f4ed6f05476ba982726932b0298efee7da4a5267980eb176f12d6e68
+  data.tar.gz: 74683875ccfeeed68fc7cdf13af16a7694b81ada533f9138165c26ff6a3e0cfa
 SHA512:
-  metadata.gz: 5596e607f371f5b05503d25fc749964af5dd3b945a3ec5011efcb4262a03c3325ea344a00e103cea13cf76e85bea41f10d4633d7f6f3a67dfeb17a7cbe04f2ea
-  data.tar.gz: d25fff95fbb51bd7b414e3e29104b798a8b5d6f11e1a4711266c16cadd532a436463be6ad0414acdda7904562a196b262738483a05e7cfa73d2138ebb4022200
+  metadata.gz: 19701f96beaeee111eaa2d9381b833a13a0954ea1e6deab9dc7095021ae95c809bf4a96abe04b2cbbe10d9d21902b3bdb5520e162151894931365f2bc188aef8
+  data.tar.gz: bf7b0fe93336654c06d58a852f88c89725974759ed30da89575b3559be5c4658ef60c3def92b50f1a4afaca3659996b0f79a9b245e7a0e9f1161b0fc05feb68e

data/CHANGELOG.md

@@ -1,3 +1,8 @@
+## 0.10.0
+* Adds the `format_parser_inspect` binary for parsing a file from the commandline
+  and returning results in JSON
+* Adds the `FormatParser.parse_at(path)` convenience method
+
 ## 0.9.4
 * Fix a TIFF parsing regression introduced in 0.3.1 that led to all TIFFs being incorrectly parsed
 

data/exe/format_parser_inspect

@@ -0,0 +1,44 @@
+#!/usr/bin/env ruby
+
+require_relative '../lib/format_parser'
+require 'json'
+require 'optparse'
+
+options = {results: :first}
+OptionParser.new do |opts|
+  opts.banner = 'Usage: format_parser_inspect --first my_file.jpg'
+  opts.on('-a', '--all', 'Return all results instead of just the first one') do |_v|
+    options[:results] = :all
+  end
+  opts.on('--natures[=NATURES]', 'Only scan specific natures (comma-separated: image, audio)', Array) do |v|
+    options[:natures] = v.map { |e| e.strip.downcase.to_sym }
+  end
+  opts.on('--formats[=FORMATS]', 'Only scan specific formats (comma-separated: jpg, tif)', Array) do |v|
+    options[:formats] = v.map { |e| e.strip.downcase.to_sym }
+  end
+end.parse!
+
+did_detect = false
+return_values = ARGV.map do |path_or_url|
+  method_name = path_or_url =~ /^http(s?)\:\/\// ? :parse_http : :parse_file_at
+  result_or_results = FormatParser.public_send(method_name, path_or_url, **options)
+  if options[:results] != :first
+    did_detect = true if result_or_results.any?
+    {
+      source_path_or_url: path_or_url,
+      options: options,
+      ambiguous: result_or_results.length > 1,
+      results: result_or_results,
+    }
+  else
+    did_detect = true if result_or_results
+    {
+      source_path_or_url: path_or_url,
+      options: options,
+      result: result_or_results,
+    }
+  end
+end
+
+puts JSON.pretty_generate(return_values)
+did_detect ? exit(0) : exit(1)

data/lib/format_parser.rb

@@ -72,6 +72,18 @@ module FormatParser
     parse(RemoteIO.new(url), **kwargs)
   end
 
+  # Parses the file at the given `path` and returns the results as if it were any IO
+  # given to `.parse`. The accepted keyword arguments are the same as the ones for `parse`.
+  #
+  # @param path[String] the path to the file to parse on the local filesystem
+  # @param kwargs the keyword arguments to be delegated to `.parse`
+  # @see {.parse}
+  def self.parse_file_at(path, **kwargs)
+    File.open(path, 'rb') do |io|
+      parse(io, **kwargs)
+    end
+  end
+
   # Parses the resource contained in the given IO-ish object, and returns either the first matched
   # result (omitting all the other parsers), the first N results or all results.
   #

data/lib/format_parser/version.rb

@@ -1,3 +1,3 @@
 module FormatParser
-  VERSION = '0.9.4'
+  VERSION = '0.10.0'
 end

data/spec/format_parser_inspect_spec.rb

@@ -0,0 +1,57 @@
+require 'spec_helper'
+require 'shellwords'
+
+describe '/exe/format_parser_inspect binary' do
+  let(:bin_path) do
+    Shellwords.escape(File.expand_path(__dir__ + '/../exe/format_parser_inspect'))
+  end
+
+  it 'performs parsing on full default' do
+    fixture_path = fixtures_dir + 'JPEG/divergent_pixel_dimensions_exif.jpg'
+
+    result = `#{bin_path} #{Shellwords.escape(fixture_path)}`
+
+    retval = JSON.parse(result, symbolize_names: true)
+    parsed_result = retval.first
+    expect(parsed_result[:source_path_or_url]).to end_with('divergent_pixel_dimensions_exif.jpg')
+    expect(parsed_result[:options][:results]).to eq('first')
+    expect(parsed_result[:result]).not_to be_nil
+  end
+
+  it 'performs parsing with --all' do
+    fixture_path = fixtures_dir + 'JPEG/divergent_pixel_dimensions_exif.jpg'
+
+    result = `#{bin_path} --all #{Shellwords.escape(fixture_path)}`
+
+    retval = JSON.parse(result, symbolize_names: true)
+    parsed_result = retval.first
+    expect(parsed_result[:source_path_or_url]).to end_with('divergent_pixel_dimensions_exif.jpg')
+    expect(parsed_result[:options][:results]).to eq('all')
+    expect(parsed_result[:ambiguous]).to eq(false)
+    expect(parsed_result[:results]).not_to be_empty
+  end
+
+  it 'performs parsing with --natures option' do
+    fixture_path = fixtures_dir + 'JPEG/divergent_pixel_dimensions_exif.jpg'
+
+    result = `#{bin_path} --natures=IMAGE #{Shellwords.escape(fixture_path)}`
+
+    retval = JSON.parse(result, symbolize_names: true)
+    parsed_result = retval.first
+    expect(parsed_result[:source_path_or_url]).to end_with('divergent_pixel_dimensions_exif.jpg')
+    expect(parsed_result[:options][:natures]).to eq(['image'])
+    expect(parsed_result[:result]).not_to be_nil
+  end
+
+  it 'performs parsing with --formats option' do
+    fixture_path = fixtures_dir + 'JPEG/divergent_pixel_dimensions_exif.jpg'
+
+    result = `#{bin_path} --formats=zip #{Shellwords.escape(fixture_path)}`
+
+    retval = JSON.parse(result, symbolize_names: true)
+    parsed_result = retval.first
+    expect(parsed_result[:source_path_or_url]).to end_with('divergent_pixel_dimensions_exif.jpg')
+    expect(parsed_result[:options][:formats]).to eq(['zip'])
+    expect(parsed_result[:result]).to be_nil
+  end
+end

data/spec/format_parser_spec.rb

@@ -47,7 +47,7 @@ describe FormatParser do
     let(:audio) { FormatParser::Audio.new(format: :aiff, num_audio_channels: 1) }
     let(:image) { FormatParser::Image.new(format: :dpx, width_px: 1, height_px: 1) }
 
-    context '#parse called hash options' do
+    context '.parse called with options' do
       before do
         expect_any_instance_of(FormatParser::AIFFParser).to receive(:call).and_return(audio)
         expect_any_instance_of(FormatParser::DPXParser).to receive(:call).and_return(image)
@@ -59,7 +59,7 @@ describe FormatParser do
       it { is_expected.to include(audio) }
     end
 
-    context '#parse called without hash options' do
+    context '.parse called without hash options' do
       before do
         expect_any_instance_of(FormatParser::DPXParser).to receive(:call).and_return(image)
       end
@@ -70,6 +70,14 @@ describe FormatParser do
     end
   end
 
+  describe '.parse_file_at' do
+    it 'parses a fixture when given a path to it' do
+      path = fixtures_dir + '/WAV/c_M1F1-Alaw-AFsp.wav'
+      result = FormatParser.parse_file_at(path)
+      expect(result.nature).to eq(:audio)
+    end
+  end
+
   describe 'when parsing fixtures' do
     Dir.glob(fixtures_dir + '/**/*.*').sort.each do |fixture_path|
       it "parses #{fixture_path} without raising any errors" do

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: format_parser
 version: !ruby/object:Gem::Version
-  version: 0.9.4
+  version: 0.10.0
 platform: ruby
 authors:
 - Noah Berman
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2018-04-22 00:00:00.000000000 Z
+date: 2018-04-23 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: ks
@@ -144,7 +144,8 @@ description: |-
 email:
 - noah@noahberman.org
 - me@julik.nl
-executables: []
+executables:
+- format_parser_inspect
 extensions: []
 extra_rdoc_files: []
 files:
@@ -159,6 +160,7 @@ files:
 - LICENSE.txt
 - README.md
 - Rakefile
+- exe/format_parser_inspect
 - format_parser.gemspec
 - lib/archive.rb
 - lib/attributes_json.rb
@@ -201,6 +203,7 @@ files:
 - spec/care_spec.rb
 - spec/esoteric_formats_spec.rb
 - spec/file_information_spec.rb
+- spec/format_parser_inspect_spec.rb
 - spec/format_parser_spec.rb
 - spec/io_utils_spec.rb
 - spec/measurometer_spec.rb
@@ -247,7 +250,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 2.5.2
+rubygems_version: 2.7.3
 signing_key: 
 specification_version: 4
 summary: A library for efficient parsing of file metadata