elasticsearch-git 0.0.1

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 1a7d0d063702f3bcc2f71f5a8ad9b55ec0377280
+  data.tar.gz: 656199334b4345491eddb15fd3f4e3ffd0a0b597
+SHA512:
+  metadata.gz: bf49c347091bb8866356b74bed98b9652b44474d7e5e5341257f06bf759a0eaf48efdf46ccdafa4211a2a7d3e98d390f33ff3b59900a3f7bc737c1020b25be75
+  data.tar.gz: 99870c02c0532ed6f72b70ee7e962c778148d7bb794a73f20eebd0cafa74e859baf1fbc1d3443fcb90b87280d06018f40f43d8299651a7413985588b218f2c6e

data/.gitignore

@@ -0,0 +1,17 @@
+*.gem
+*.rbc
+.bundle
+.config
+.yardoc
+Gemfile.lock
+InstalledFiles
+_yardoc
+coverage
+doc/
+lib/bundler/man
+pkg
+rdoc
+spec/reports
+test/tmp
+test/version_tmp
+tmp

data/Gemfile

@@ -0,0 +1,16 @@
+source 'https://rubygems.org'
+
+# Specify your gem's dependencies in elasticsearch-git.gemspec
+gemspec
+
+gem 'elasticsearch-model', github: 'elasticsearch/elasticsearch-rails'
+gem 'elasticsearch-api', git: 'git://github.com/elasticsearch/elasticsearch-ruby.git'
+gem 'rugged', git: 'git://github.com/libgit2/rugged.git', branch: 'development', submodules: true
+gem 'bundler'
+gem 'rake'
+gem 'pry'
+gem 'gitlab_git'
+gem 'minitest'
+gem 'activesupport', '> 4.0.0'
+gem 'activemodel', '> 4.0.0'
+gem 'wrong'

data/LICENSE.txt

@@ -0,0 +1,22 @@
+Copyright (c) 2014 Andrey Kumanyaev
+
+MIT License
+
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of this software and associated documentation files (the
+"Software"), to deal in the Software without restriction, including
+without limitation the rights to use, copy, modify, merge, publish,
+distribute, sublicense, and/or sell copies of the Software, and to
+permit persons to whom the Software is furnished to do so, subject to
+the following conditions:
+
+The above copyright notice and this permission notice shall be
+included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
+LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
+OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
+WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

data/README.md

@@ -0,0 +1,57 @@
+# Elasticsearch::Git
+
+Attention: Pre-pre-pre beta code. Not production.
+
+[Elasticsearch](https://github.com/elasticsearch/elasticsearch-rails/tree/master/elasticsearch-model) integrations for git repositories
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+``` ruby
+gem 'elasticsearch-git'
+```
+
+And then execute:
+
+``` bash
+$ bundle
+```
+
+Or install it yourself as:
+
+``` bash
+$ gem install elasticsearch-git
+```
+
+## Usage
+
+``` ruby
+class Repository
+  include Elasticsearch::Git::Repository
+
+  set_repository_id       project.id
+  repository_for_indexing '/path/to/your/repo'
+
+end
+
+Repository.__elasticsearch__.create_index! force: true
+
+repo = Repository.new
+repo.index_commits
+repo.index_blobs
+
+Repository.search("query", type: 'blob')
+Repository.search("query", type: 'commit')
+
+# Search in all types
+Repository.search("query")
+```
+
+## Contributing
+
+1. Fork it ( http://github.com/[my-github-username]/elasticsearch-git/fork )
+2. Create your feature branch (`git checkout -b my-new-feature`)
+3. Commit your changes (`git commit -am 'Add some feature'`)
+4. Push to the branch (`git push origin my-new-feature`)
+5. Create new Pull Request

data/Rakefile

@@ -0,0 +1 @@
+require "bundler/gem_tasks"

data/elasticsearch-git.gemspec

@@ -0,0 +1,27 @@
+# coding: utf-8
+lib = File.expand_path('../lib', __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require 'elasticsearch/git/version'
+
+Gem::Specification.new do |spec|
+  spec.name          = "elasticsearch-git"
+  spec.version       = Elasticsearch::Git::VERSION
+  spec.authors       = ["Andrey Kumanyaev"]
+  spec.email         = ["me@zzet.org"]
+  spec.summary       = %q{Elasticsearch integrations for git repositories.}
+  spec.description   = %q{Elasticsearch integrations for git repositories.}
+  spec.homepage      = "https://github.com/zzet/elasticsearch-git"
+  spec.license       = "MIT"
+
+  spec.files         = `git ls-files -z`.split("\x0")
+  spec.executables   = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
+  spec.test_files    = spec.files.grep(%r{^(test|spec|features)/})
+  spec.require_paths = ["lib"]
+
+  spec.add_runtime_dependency 'elasticsearch-model'
+  spec.add_runtime_dependency 'elasticsearch-api'
+  spec.add_runtime_dependency 'rugged'
+  spec.add_runtime_dependency 'gitlab_git'
+  spec.add_runtime_dependency 'activemodel'
+  spec.add_runtime_dependency 'activesupport'
+end

data/lib/elasticsearch/git.rb

@@ -0,0 +1,12 @@
+require "elasticsearch/git/version"
+require "elasticsearch/git/model"
+require "elasticsearch/git/commit"
+
+module Elasticsearch
+  module Git
+    class Test
+      include Elasticsearch::Git::Model
+    end
+  end
+end
+

data/lib/elasticsearch/git/model.rb

@@ -0,0 +1,68 @@
+require 'active_support/concern'
+require 'active_model'
+require 'elasticsearch/model'
+
+module Elasticsearch
+  module Git
+    module Model
+      extend ActiveSupport::Concern
+
+      included do
+        extend ActiveModel::Naming
+        include ActiveModel::Model
+        include Elasticsearch::Model
+
+        index_name [self.name.downcase, 'index', Rails.env.to_s].join('-')
+
+        settings \
+          index: {
+          analysis: {
+            analyzer: {
+              human_analyzer: {
+                type: 'custom',
+                tokenizer: 'human_tokenizer',
+                filter: %w(lowercase asciifolding human_ngrams)
+              },
+              sha_analyzer: {
+                type: 'custom',
+                tokenizer: 'sha_tokenizer',
+                filter: %w(lowercase asciifolding sha_ngrams)
+              },
+              code_analyzer: {
+                type: 'custom',
+                tokenizer: 'standard',
+                filter: %w(lowercase asciifolding)
+              }
+            },
+            tokenizer: {
+              sha_tokenizer: {
+                type: "NGram",
+                min_gram: 8,
+                max_gram: 40,
+                token_chars: %w(letter digit)
+              },
+              human_tokenizer: {
+                type: "NGram",
+                min_gram: 1,
+                max_gram: 20,
+                token_chars: %w(letter digit)
+              }
+            },
+            filter: {
+              human_ngrams: {
+                type: "NGram",
+                min_gram: 1,
+                max_gram: 20
+              },
+              sha_ngrams: {
+                type: "NGram",
+                min_gram: 8,
+                max_gram: 40
+              }
+            }
+          }
+        }
+      end
+    end
+  end
+end

data/lib/elasticsearch/git/repository.rb

@@ -0,0 +1,200 @@
+require 'active_support/concern'
+require 'active_model'
+require 'elasticsearch'
+require 'elasticsearch/model'
+require 'rugged'
+require 'gitlab_git'
+
+module Elasticsearch
+  module Git
+    module Repository
+      extend ActiveSupport::Concern
+
+      included do
+        include Elasticsearch::Git::Model
+
+        mapping do
+          indexes :blobs do
+            indexes :id,          type: :string, index_options: 'offsets', search_analyzer: :human_analyzer,  index_analyzer: :human_analyzer
+            indexes :oid,         type: :string, index_options: 'offsets', search_analyzer: :sha_analyzer,    index_analyzer: :sha_analyzer
+            indexes :commit_sha,  type: :string, index_options: 'offsets', search_analyzer: :sha_analyzer,    index_analyzer: :sha_analyzer
+            indexes :content,     type: :string, index_options: 'offsets', search_analyzer: :code_analyzer,   index_analyzer: :human_analyzer
+          end
+          indexes :commits do
+            indexes :id,          type: :string, index_options: 'offsets', search_analyzer: :human_analyzer,  index_analyzer: :human_analyzer
+            indexes :sha,         type: :string, index_options: 'offsets', search_analyzer: :sha_analyzer,    index_analyzer: :sha_analyzer
+            indexes :author do
+              indexes :name,      type: :string, index_options: 'offsets', search_analyzer: :code_analyzer,    index_analyzer: :human_analyzer
+              indexes :email,     type: :string, index_options: 'offsets', search_analyzer: :code_analyzer,    index_analyzer: :human_analyzer
+              indexes :time,      type: :date
+            end
+            indexes :commiter do
+              indexes :name,      type: :string, index_options: 'offsets', search_analyzer: :code_analyzer,    index_analyzer: :human_analyzer
+              indexes :email,     type: :string, index_options: 'offsets', search_analyzer: :code_analyzer,    index_analyzer: :human_analyzer
+              indexes :time,      type: :date
+            end
+            indexes :message,    type: :string, index_options: 'offsets', search_analyzer: :code_analyzer,     index_analyzer: :human_analyzer
+          end
+        end
+
+        # Indexing all text-like blobs in repository
+        #
+        # All data stored in global index
+        # Repository can be selected by 'rid' field
+        # If you want - this field can be used for store 'project' id
+        #
+        # blob {
+        #   id - uniq id of blob from all repositories
+        #   oid - blob id in repository
+        #   content - blob content
+        #   commit_sha - last actual commit sha
+        # }
+        #
+        # For search from blobs use type 'blob'
+        def index_blobs
+          target_sha = repository_for_indexing.head.target
+          repository_for_indexing.index.each do |blob|
+            b = LiteBlob.new(repository_for_indexing, blob)
+            if b.text?
+              client_for_indexing.index \
+                index: "#{self.class.index_name}",
+                type: "blob",
+                id: "#{repository_id}_#{b.path}",
+                body: {
+                  blob: {
+                    oid: b.id,
+                    rid: repository_id,
+                    content: b.data,
+                    commit_sha: target_sha
+                  }
+                }
+            end
+          end
+        end
+
+        # Indexing all commits in repository
+        #
+        # All data stored in global index
+        # Repository can be filtered by 'rid' field
+        # If you want - this field can be used git store 'project' id
+        #
+        # commit {
+        #  sha - commit sha
+        #  author {
+        #    name - commit author name
+        #    email - commit author email
+        #    time - commit time
+        #  }
+        #  commiter {
+        #    name - committer name
+        #    email - committer email
+        #    time - commit time
+        #  }
+        #  message - commit message
+        # }
+        #
+        # For search from commits use type 'commit'
+        def index_commits
+          repository_for_indexing.each_id do |oid|
+            obj = repository_for_indexing.lookup(oid)
+            if obj.type == :commit
+              client_for_indexing.index \
+                index: "#{self.class.index_name}",
+                type: "commit",
+                id: "#{repository_id}_#{obj.oid}",
+                body: {
+                  commit: {
+                    rid: repository_id,
+                    sha: obj.oid,
+                    author: obj.author,
+                    committer: obj.committer,
+                    message: obj.message
+                  }
+                }
+            end
+          end
+        end
+
+        # Representation of repository as indexed json
+        # Attention: It can be very very very huge hash
+        def as_indexed_json(options = {})
+          ij = {}
+          ij[:blobs] = index_blobs_array
+          ij[:commits] = index_commits_array
+          ij
+        end
+
+        # Indexing blob from current index
+        def index_blobs_array
+          result = []
+
+          target_sha = repository_for_indexing.head.target
+          repository_for_indexing.index.each do |blob|
+            b = EasyBlob.new(repository_for_indexing, blob)
+            result.push(
+              {
+                id: "#{target_sha}_#{b.path}",
+                oid: b.id,
+                content: b.data,
+                commit_sha: target_sha
+              }
+            ) if b.text?
+          end
+
+          result
+        end
+
+        # Lookup all object ids for commit objects
+        def index_commits_array
+          res = []
+
+          repository_for_indexing.each_id do |oid|
+            obj = repository_for_indexing.lookup(oid)
+            if obj.type == :commit
+              res.push(
+                {
+                  sha: obj.oid,
+                  author: obj.author,
+                  committer: obj.committer,
+                  message: obj.message
+                }
+              )
+            end
+          end
+
+          res
+        end
+
+        # Repository id used for identity data from different repositories
+        # Update this value if need
+        def set_repository_id id
+          @repository_id = id || path_to_repo
+        end
+
+        def repository_for_indexing(repo_path = "")
+          @path_to_repo ||= repo_path
+          Rugged::Repository.new(@path_to_repo)
+        end
+
+        def client_for_indexing
+          @client_for_indexing ||= Elasticsearch::Client.new log: true
+        end
+
+      end
+    end
+
+    class LiteBlob
+      include Linguist::BlobHelper
+      include EncodingHelper
+
+      attr_accessor :id, :name, :path, :data, :commit_id
+
+      def initialize(repo, raw_blob_hash)
+        @id = raw_blob_hash[:oid]
+        @path = raw_blob_hash[:path]
+        @name = @path.split("/").last
+        @data = encode!(repo.lookup(@id).content)
+      end
+    end
+  end
+end

data/lib/elasticsearch/git/version.rb

@@ -0,0 +1,5 @@
+module Elasticsearch
+  module Git
+    VERSION = "0.0.1"
+  end
+end

data/lib/test/test_helper.rb

@@ -0,0 +1,21 @@
+require "rubygems"
+require 'bundler/setup'
+require 'pry'
+
+Bundler.require
+
+require 'wrong/adapters/minitest'
+
+PROJECT_ROOT = File.join(Dir.pwd)
+
+Wrong.config.color
+
+Minitest.autorun
+
+class TestCase < Minitest::Test
+  include Wrong
+
+  def fixtures_path
+    @path ||= File.expand_path(File.join(__FILE__, "../fixtures"))
+  end
+end

metadata

@@ -0,0 +1,139 @@
+--- !ruby/object:Gem::Specification
+name: elasticsearch-git
+version: !ruby/object:Gem::Version
+  version: 0.0.1
+platform: ruby
+authors:
+- Andrey Kumanyaev
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2014-02-16 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: elasticsearch-model
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: elasticsearch-api
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: rugged
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: gitlab_git
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: activemodel
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: activesupport
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+description: Elasticsearch integrations for git repositories.
+email:
+- me@zzet.org
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- .gitignore
+- Gemfile
+- LICENSE.txt
+- README.md
+- Rakefile
+- elasticsearch-git.gemspec
+- lib/elasticsearch/git.rb
+- lib/elasticsearch/git/model.rb
+- lib/elasticsearch/git/repository.rb
+- lib/elasticsearch/git/version.rb
+- lib/test/test_helper.rb
+homepage: https://github.com/zzet/elasticsearch-git
+licenses:
+- MIT
+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: 2.0.3
+signing_key: 
+specification_version: 4
+summary: Elasticsearch integrations for git repositories.
+test_files: []