cmp_text 0.1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: d069032baea088c441aaa2d33894d345a5001d56
+  data.tar.gz: e305a7c9e08df175b34239fc7481fe6652d2a072
+SHA512:
+  metadata.gz: c57ac15b41faa1d00c32806e7864956d00e7eecb4a1a61f7b838dda8ce17128bbfa124ed1c8bc0fe72c432e2dcc212691e9cdbde1ad85a8630b53357d23e8d10
+  data.tar.gz: e36870c76c907eb2c3a7b1d90c6e8bf64a37d311595c56d6bfcf26ca9b100c3fffcd5ea637dd05d388e88a22cd063d1ba0d34a83f57f8bfed1ed7e6ee2745a82

data/.gitignore

@@ -0,0 +1,12 @@
+/.bundle/
+/.yardoc
+/Gemfile.lock
+/_yardoc/
+/coverage/
+/doc/
+/pkg/
+/spec/reports/
+/tmp/
+
+# rspec failure tracking
+.rspec_status

data/.rspec

@@ -0,0 +1,2 @@
+--format documentation
+--color

data/.travis.yml

@@ -0,0 +1,5 @@
+sudo: false
+language: ruby
+rvm:
+  - 2.3.3
+before_install: gem install bundler -v 1.15.3

data/CODE_OF_CONDUCT.md

@@ -0,0 +1,74 @@
+# Contributor Covenant Code of Conduct
+
+## Our Pledge
+
+In the interest of fostering an open and welcoming environment, we as
+contributors and maintainers pledge to making participation in our project and
+our community a harassment-free experience for everyone, regardless of age, body
+size, disability, ethnicity, gender identity and expression, level of experience,
+nationality, personal appearance, race, religion, or sexual identity and
+orientation.
+
+## Our Standards
+
+Examples of behavior that contributes to creating a positive environment
+include:
+
+* Using welcoming and inclusive language
+* Being respectful of differing viewpoints and experiences
+* Gracefully accepting constructive criticism
+* Focusing on what is best for the community
+* Showing empathy towards other community members
+
+Examples of unacceptable behavior by participants include:
+
+* The use of sexualized language or imagery and unwelcome sexual attention or
+advances
+* Trolling, insulting/derogatory comments, and personal or political attacks
+* Public or private harassment
+* Publishing others' private information, such as a physical or electronic
+  address, without explicit permission
+* Other conduct which could reasonably be considered inappropriate in a
+  professional setting
+
+## Our Responsibilities
+
+Project maintainers are responsible for clarifying the standards of acceptable
+behavior and are expected to take appropriate and fair corrective action in
+response to any instances of unacceptable behavior.
+
+Project maintainers have the right and responsibility to remove, edit, or
+reject comments, commits, code, wiki edits, issues, and other contributions
+that are not aligned to this Code of Conduct, or to ban temporarily or
+permanently any contributor for other behaviors that they deem inappropriate,
+threatening, offensive, or harmful.
+
+## Scope
+
+This Code of Conduct applies both within project spaces and in public spaces
+when an individual is representing the project or its community. Examples of
+representing a project or community include using an official project e-mail
+address, posting via an official social media account, or acting as an appointed
+representative at an online or offline event. Representation of a project may be
+further defined and clarified by project maintainers.
+
+## Enforcement
+
+Instances of abusive, harassing, or otherwise unacceptable behavior may be
+reported by contacting the project team at mico_xiaozhen@sina.com. All
+complaints will be reviewed and investigated and will result in a response that
+is deemed necessary and appropriate to the circumstances. The project team is
+obligated to maintain confidentiality with regard to the reporter of an incident.
+Further details of specific enforcement policies may be posted separately.
+
+Project maintainers who do not follow or enforce the Code of Conduct in good
+faith may face temporary or permanent repercussions as determined by other
+members of the project's leadership.
+
+## Attribution
+
+This Code of Conduct is adapted from the [Contributor Covenant][homepage], version 1.4,
+available at [http://contributor-covenant.org/version/1/4][version]
+
+[homepage]: http://contributor-covenant.org
+[version]: http://contributor-covenant.org/version/1/4/

data/Gemfile

@@ -0,0 +1,6 @@
+source "https://rubygems.org"
+
+git_source(:github) {|repo_name| "https://github.com/#{repo_name}" }
+
+# Specify your gem's dependencies in cmp_text.gemspec
+gemspec

data/README.md

@@ -0,0 +1,39 @@
+# CmpText
+
+Welcome to your new gem! In this directory, you'll find the files you need to be able to package up your Ruby library into a gem. Put your Ruby code in the file `lib/cmp_text`. To experiment with that code, run `bin/console` for an interactive prompt.
+
+TODO: Delete this and the text above, and describe your gem
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+```ruby
+gem 'cmp_text'
+```
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install cmp_text
+
+## Usage
+
+TODO: Write usage instructions here
+
+## Development
+
+After checking out the repo, run `bin/setup` to install dependencies. Then, run `rake spec` to run the tests. You can also run `bin/console` for an interactive prompt that will allow you to experiment.
+
+To install this gem onto your local machine, run `bundle exec rake install`. To release a new version, update the version number in `version.rb`, and then run `bundle exec rake release`, which will create a git tag for the version, push git commits and tags, and push the `.gem` file to [rubygems.org](https://rubygems.org).
+
+## Contributing
+
+Bug reports and pull requests are welcome on GitHub at https://github.com/[USERNAME]/cmp_text. This project is intended to be a safe, welcoming space for collaboration, and contributors are expected to adhere to the [Contributor Covenant](http://contributor-covenant.org) code of conduct.
+
+## Code of Conduct
+
+Everyone interacting in the CmpText project’s codebases, issue trackers, chat rooms and mailing lists is expected to follow the [code of conduct](https://github.com/[USERNAME]/cmp_text/blob/master/CODE_OF_CONDUCT.md).

data/Rakefile

@@ -0,0 +1,6 @@
+require "bundler/gem_tasks"
+require "rspec/core/rake_task"
+
+RSpec::Core::RakeTask.new(:spec)
+
+task :default => :spec

data/bin/console

@@ -0,0 +1,14 @@
+#!/usr/bin/env ruby
+
+require "bundler/setup"
+require "cmp_text"
+
+# You can add fixtures and/or initialization code here to make experimenting
+# with your gem easier. You can also use a different console, if you like.
+
+# (If you use this, don't forget to add pry to your Gemfile!)
+# require "pry"
+# Pry.start
+
+require "irb"
+IRB.start(__FILE__)

data/bin/setup

@@ -0,0 +1,8 @@
+#!/usr/bin/env bash
+set -euo pipefail
+IFS=$'\n\t'
+set -vx
+
+bundle install
+
+# Do any other automated setup that you need to do here

data/cmp_text.gemspec

@@ -0,0 +1,35 @@
+# coding: utf-8
+lib = File.expand_path("../lib", __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require "cmp_text/version"
+
+Gem::Specification.new do |spec|
+  spec.name          = "cmp_text"
+  spec.version       = CmpText::VERSION
+  spec.authors       = ["zhouxiaozhen"]
+  spec.email         = ["mico_xiaozhen@sina.com"]
+
+  spec.summary       = '比较两个文件中文字相似度,也可以直接比较2段文字'
+  spec.description   = '比较两个文件中文字相似度,也可以直接比较2段文字'
+  spec.homepage      = ""
+
+  # Prevent pushing this gem to RubyGems.org. To allow pushes either set the 'allowed_push_host'
+  # to allow pushing to a single host or delete this section to allow pushing to any host.
+  # if spec.respond_to?(:metadata)
+  #   spec.metadata["allowed_push_host"] = "TODO: Set to 'http://mygemserver.com'"
+  # else
+  #   raise "RubyGems 2.0 or newer is required to protect against " \
+  #     "public gem pushes."
+  # end
+
+  spec.files         = `git ls-files -z`.split("\x0").reject do |f|
+    f.match(%r{^(test|spec|features)/})
+  end
+  spec.bindir        = "exe"
+  spec.executables   = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
+  spec.require_paths = ["lib"]
+
+  spec.add_development_dependency "bundler", "~> 1.15"
+  spec.add_development_dependency "rake", "~> 10.0"
+  spec.add_development_dependency "rspec", "~> 3.0"
+end

data/lib/cmp_text/version.rb

@@ -0,0 +1,3 @@
+module CmpText
+  VERSION = "0.1.0"
+end

data/lib/cmp_text.rb

@@ -0,0 +1,64 @@
+require "cmp_text/version"
+
+module CmpText
+  class Analysis
+    class << self
+      attr_accessor :log_text
+
+      def open(file)
+        File.file?(file) ? File.open(file).read.chomp.strip.gsub(/'/, '') : file.to_s.dup
+      end
+
+      def txt_cmp(f0, f1)
+        str_f0, str_f1 = open(f0), open(f1)
+
+        @log_text = {
+          or_text_1: str_f0.dup,
+          or_text_2: str_f1.dup,
+          succ_char:[],
+          failed_char: []
+        }
+
+        arr_f0_each_char = str_f0.dup.split('')
+        arr_f1_each_char = str_f1.dup.split('')
+        str_f0_size = str_f0.dup.size
+        str_f1_size = str_f1.dup.size
+
+        arr_f0_each_char.each_with_index do |char, index|
+          cmp = false
+          break if [arr_f0_each_char.size, arr_f1_each_char.size].any?{|size| size == 0}
+          to_index = index
+
+          while str_f1.include?(char) do
+            if [str_f0_size, str_f1_size].min < (to_index + 1)
+              cmp = true
+              break
+            end
+            to_index += 1
+            char = arr_f0_each_char[index..to_index].join
+          end
+
+          to_index -= 1 unless [str_f0_size, str_f1_size].min == (to_index + 1) && cmp
+          if (to_index - index) > 0 || (to_index - index == 0 && ([str_f0_size,   str_f1_size].min == 1))
+            succ_char = arr_f0_each_char.slice!(index..to_index).join
+            arr_f0_each_char.unshift(nil)
+            arr_f1_each_char = arr_f1_each_char.join.sub(succ_char,'').split
+            @log_text[:succ_char] << succ_char
+          end
+        end
+
+        @log_text[:failed_char] << arr_f1_each_char.join << arr_f0_each_char.join
+        @log_text[:failed_char].delete('')
+
+        "#{(
+            (@log_text[:succ_char].join.size.to_f / [ @log_text[:or_text_1].size.to_f, @log_text[:or_text_2].size.to_f].max ) * 100
+          ).round(3)
+        }%".strip
+      end
+    end
+  end
+end
+
+
+
+

metadata

@@ -0,0 +1,97 @@
+--- !ruby/object:Gem::Specification
+name: cmp_text
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- zhouxiaozhen
+autorequire: 
+bindir: exe
+cert_chain: []
+date: 2018-05-16 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.15'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.15'
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '10.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '10.0'
+- !ruby/object:Gem::Dependency
+  name: rspec
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.0'
+description: 比较两个文件中文字相似度,也可以直接比较2段文字
+email:
+- mico_xiaozhen@sina.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- ".gitignore"
+- ".rspec"
+- ".travis.yml"
+- CODE_OF_CONDUCT.md
+- Gemfile
+- README.md
+- Rakefile
+- bin/console
+- bin/setup
+- cmp_text.gemspec
+- lib/cmp_text.rb
+- lib/cmp_text/version.rb
+homepage: ''
+licenses: []
+metadata: {}
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 2.6.12
+signing_key: 
+specification_version: 4
+summary: 比较两个文件中文字相似度,也可以直接比较2段文字
+test_files: []