ezgff 0.0.2

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: c5243c27b01a1b9c51ca19784b7fcce0cc86766de41270aa1a546370d1dcda9c
+  data.tar.gz: 06a3a2491430b10e33bae1e89c4a32d52feaab7a93425de47d6d3a0b15d6de23
+SHA512:
+  metadata.gz: cfe588ee8d77d84540ade9b87cc3d3f6393e87cff783039959105a09a1fd9d6a94fd58aac1ee0964061112db6a5ba3dde4292bc9b4db8e2effee4b6f27bec703
+  data.tar.gz: cf1f4a39764e43456686fe7da5e7cae3cf1bbc2fba55b78ef9d4f52dd6ea232186a944b320a506bfc6499077e98d921ac6933fb774034d19323430724c1b5091

data/.gitignore

@@ -0,0 +1,56 @@
+*.gem
+*.rbc
+/.config
+/coverage/
+/InstalledFiles
+/pkg/
+/spec/reports/
+/spec/examples.txt
+/test/tmp/
+/test/version_tmp/
+/tmp/
+
+# Used by dotenv library to load environment variables.
+# .env
+
+# Ignore Byebug command history file.
+.byebug_history
+
+## Specific to RubyMotion:
+.dat*
+.repl_history
+build/
+*.bridgesupport
+build-iPhoneOS/
+build-iPhoneSimulator/
+
+## Specific to RubyMotion (use of CocoaPods):
+#
+# We recommend against adding the Pods directory to your .gitignore. However
+# you should judge for yourself, the pros and cons are mentioned at:
+# https://guides.cocoapods.org/using/using-cocoapods.html#should-i-check-the-pods-directory-into-source-control
+#
+# vendor/Pods/
+
+## Documentation cache and generated files:
+/.yardoc/
+/_yardoc/
+/doc/
+/rdoc/
+
+## Environment normalization:
+/.bundle/
+/vendor/bundle
+/lib/bundler/man/
+
+# for a library or gem, you might want to ignore these files since the code is
+# intended to run in multiple environments; otherwise, check them in:
+# Gemfile.lock
+# .ruby-version
+# .ruby-gemset
+
+# unless supporting rvm < 1.11.0 or doing something fancy, ignore this:
+.rvmrc
+
+# Used by RuboCop. Remote config files pulled in from inherit_from directive.
+# .rubocop-https?--*

data/Gemfile

@@ -0,0 +1,14 @@
+source "https://rubygems.org"
+
+# Specify your gem's dependencies in ezgff.gemspec
+gemspec
+
+gem "rake", "~> 12.0"
+gem "rspec", "~> 3.0"
+
+gem "sqlite3"
+gem "color_echo"
+gem "bio"
+gem "thor"
+
+

data/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2021 Shuji Shigenobu
+
+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 +1,34 @@
+# ezgff_alpha
+
+## What is ezgff_alpha
+
+## Pre-requisites
+
+  * sqlite3
+
+## Install
+
+
+## Quick start
+
+Build database from GFF3 file.
+
+```bash
+ezgff build in.gff3
+```
+
+Retrieve GFF3 reacod by ID.
+
+```bash
+ezgff view data.ezdb cds-WP_010895901.1 --with=ancestors
+```
+
+```
+ezgff view data.ezdb cds-WP_010895901.1 --with=ancestors --format=json |jq
+```
+
+examples to use jq
+
+```
+ezgff_alpha/bin/ezgff view GCF_000009605.1_ASM960v1_genomic.gff.ezdb cds-WP_010895901.1  --with=ancestors --format=json  |jq -r '.gff_records | map(select(.type == "gene"))[0] | [.seqid, .start, .end, .attributes.gene] |@csv'
+```

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/build_gff_sqlitedb.rb

@@ -0,0 +1,91 @@
+require 'sqlite3'
+require 'bio'
+require 'json'
+
+def attributes_as_json(gffline)
+  gr = Bio::GFF::GFF3::Record.new(gffline.chomp)
+  h = Hash.new
+  gr.attributes.each do |att|
+    k, v = att
+    unless h.has_key?(k)
+      h[k] = []
+    end
+    h[k] << v
+  end
+  h2 = Hash.new
+  h.each do |k, v|
+    h2[k] = v.join(",")
+  end
+  h2.to_json
+end
+
+
+gfffile = ARGV[0]
+#gfffile = "example_gff/apisum_part.gff3"
+#gfffile = "example_gff/ApL_HF_liftover_Refseq.gff"
+
+dbname = gfffile + ".sqlite3"
+
+db = SQLite3::Database.new(dbname)
+
+sql = <<-SQL
+CREATE TABLE gff_records (
+  line_num     integer primary key,
+  record       text,
+  id           text,
+  parent       text,
+  seqid      text not null,
+  source       text,
+  type      text,
+  start        integer not null,
+  end          integer not null,
+  score        real,
+  strand       varchar(1),
+  phase        integer,
+  attributes   text,
+  attributes_json text
+);
+SQL
+
+db.execute(sql)
+
+db.transaction do 
+  File.open(gfffile).each_with_index do |l, i|
+#    puts l
+    ## skip FASTA seq section
+    break if /^\#\#FASTA/.match(l)
+
+    ## skip header section
+    next if /^\#/.match(l)
+    gr = Bio::GFF::GFF3::Record.new(l.chomp)
+#    p gr.attributes
+    id = nil
+    id_found = gr.attributes.select{|a| a[0] == "ID"}
+    if id_found.size == 1
+      id = id_found[0][1]
+    elsif id_found.size == 0
+      ## do nothing (id = nil)
+    elsif id_found > 1
+      STDERR.puts gr.attributes
+      raise "Multiple IDs found."
+    end
+    parent =  ((gr.attributes.select{|a| a[0] == "Parent"}[0]) || [])[1]
+    a = l.chomp.split(/\t/)
+
+    sql = "INSERT INTO gff_records (line_num, record, id, parent, seqid, source, type, start, end, score, strand, phase, attributes, attributes_json)
+    VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)"
+    values = [i, l.chomp, id, parent, 
+      a[0], a[1], a[2], a[3], a[4], a[5], a[6], a[7], a[8], 
+      attributes_as_json(l)]
+    db.execute(sql, values)
+  end
+end
+
+#===
+# create index
+table = "gff_records"
+%w{id parent source type}.each do |col|
+  idxname = "index_#{table}_on_#{col}"
+  sql = "CREATE INDEX #{idxname} ON #{table}(#{col})"
+  db.execute(sql)
+end

data/bin/build_gff_sqlitedb_keywords.rb

@@ -0,0 +1,70 @@
+require 'sqlite3'
+require 'bio'
+require 'json'
+require './gffsqlitedb'
+
+def insert_data(record, key, db_kw)
+  rec = record
+  att = rec.attributes
+  xdb = rec.dbxrefs
+  if val = att[key]
+    sql = "INSERT INTO gff_keywords (line_num, key, value) VALUES (?, ?, ?)"
+    values = [rec.line_num, key, val]
+    puts sql
+    p values
+    db_kw.execute(sql, values)
+  end
+end
+
+def insert_data_dbxref(record, key, db_kw)
+  rec = record
+  xdb = rec.dbxrefs
+  val = xdb[key]
+  sql = "INSERT INTO gff_keywords (line_num, key, value, category) VALUES (?, ?, ?, ?)"
+  values = [rec.line_num, key, val, "Dbxref"]
+  puts sql
+  p values
+  db_kw.execute(sql, values)
+end
+
+gfffile = ARGV[0]
+
+db_file = gfffile + ".sqlite3" # altready built
+#db_keywards = gfffile + ".keywords.sqlite3"
+
+gffdb = GffDb.new(db_file) # altready built
+db = SQLite3::Database.new(db_file)
+
+sql = <<-SQL
+CREATE TABLE gff_keywords (
+  id           integer primary key,
+  line_num     integer,
+  key          text not null,
+  value        text,
+  category     text
+);
+SQL
+
+db.execute(sql)
+
+db.transaction do 
+  gffdb.each_record do |r|
+    insert_data(r, "Name", db)
+    insert_data(r, "gbkey", db)
+    insert_data(r, "gene", db)
+    insert_data(r, "product", db)
+    insert_data(r, "transcript_id", db)
+    r.dbxrefs.keys.each do |k|
+      insert_data_dbxref(r, k, db)
+    end
+  end
+end
+
+#===
+# create index
+table = "gff_keywords"
+%w{id line_num key value}.each do |col|
+  idxname = "index_#{table}_on_#{col}"
+  sql = "CREATE INDEX #{idxname} ON #{table}(#{col})"
+  db.execute(sql)
+end

data/bin/build_gff_tabix.rb

@@ -0,0 +1,13 @@
+gfffile = ARGV[0]
+gfffile = "example_gff/apisum_part.gff3"
+#gfffile = "example_gff/ApL_HF_liftover_Refseq.gff"
+
+#=== sort gff by position
+gfffile_sorted = gfffile + ".gz"
+cmd = %Q{(grep ^"#" #{gfffile}; grep -v ^"#" #{gfffile} | sort -k1,1 -k4,4n) | bgzip > #{gfffile_sorted};}
+system cmd
+
+cmd = "tabix -p gff #{gfffile_sorted}"
+system cmd
+
+STDERR.puts "#{gfffile_sorted} and #{gfffile_sorted}.tbi were generated."

data/exe/ezgff

@@ -0,0 +1,168 @@
+#!/usr/bin/env ruby
+
+require_relative '../lib/ezgff'
+require 'thor'
+require 'color_echo/get'
+
+module Ezgff
+  class CLI < Thor
+
+    ## hack to enable -h option
+    ## ref: https://magazine.rubyist.net/articles/0046/0046-Milkode.html#%E3%82%AB%E3%82%B9%E3%82%BF%E3%83%9E%E3%82%A4%E3%82%BA-milk-add--h-%E3%82%92%E5%AE%9F%E7%8F%BE%E3%81%99%E3%82%8B
+
+    class_option :help, :type => :boolean, :aliases => '-h', :desc => 'Help message'
+
+    no_tasks do
+      def invoke_command(task, *args)
+        if options[:help] &&
+          task.name != 'grep'
+          Ezgff::CLI.task_help(shell, task.name)
+        elsif options[:version] && task.name == 'help'
+          puts "milk #{Version}"
+        else
+          super
+        end
+      end
+    end
+    ## end of -h option setting
+
+    desc "version", "show version number"
+    def version()
+      puts Ezgff::VERSION 
+    end
+
+    desc "view DB QUERY", "retrieve GFF record by ID and view it in a specified format.
+    DB     path to ezdb
+          ezdb should be created by using 'build' subcommand in advance.
+    QUERY  query for search
+          Two modes, simple mode and advanced mode are available.       
+          Simple mode
+            ID is given and search by the ID.
+          Advanced mode
+            Query is given in KEY=VALUE style. Available keys are
+            ID: ID (ex. ID=rna-XM_029485812.1)
+            LN: Line number (ex. LN=255)
+          Note: Spaces are not allowed before and after =
+            
+    "
+
+    option :format, :aliases => '-f', :enum => ["json", "gff"], :default => "gff", :desc => "Specify output format."
+    option :with, :aliases => '-w', :enum => ["none", "parent", "children", "ancestors", "descendants"], :default => "none", :desc => "Retrieve data with parent or children features."
+    option :type, :aliases => '-t', :desc => "Limit type (Column \#3 in GFF file) such as gene, mRNA and CDS"
+
+    def view(db, query)
+      ezdb = db
+      files = Dir["#{ezdb}/*.sqlite3"]
+      sq3_file = nil
+      if files.size == 1
+        sq3_file = files[0]
+      elsif files.size == 0
+        raise "sqlite3 file not found"
+      elsif files.size > 1
+        raise "Multiple sqlite3 files found"
+      end
+      sq3_db = GffDb.new(sq3_file)
+
+      if m = /^LN\=/.match(query)
+        ## search by line number
+        query2 = m.post_match.strip
+        ann = sq3_db.get_by_line_number(query2)
+      elsif m = /^ID\=/.match(query)
+        ## search by ID
+        query2 = m.post_match.strip
+        ann = sq3_db.get(query2)
+      else
+        ann = sq3_db.get(query)
+      end
+
+      results = []
+      if options[:with] == "descendants"
+        results = ann.descendants
+      elsif options[:with] == "ancestors"
+        results = ann.ancestors
+      else
+        parent = nil
+        if options[:with] == "parent"
+          parent = ann.parent
+        end
+        children = []
+        if options[:with] == "children"
+          ann.children.each do |c|
+            children << c
+          end
+        end
+
+        results = []
+        results << parent if parent
+        results << ann
+        results += children
+      end
+
+      ## Filter results
+      ## - type / type
+      if options[:type]
+        target_type = options[:type]
+        results = results.select{|r| r.type == target_type}
+      end
+
+      case options[:format]
+      when "json"
+        h = Hash.new
+        ary = results.map{|r| r.to_h}
+        h["gff_records"] = ary
+        puts h.to_json
+        
+      when "gff"
+        puts results
+      else
+        raise "Unknown format: #{options[:format]}"
+      end
+
+    end
+
+    desc "build GFF", "build database from GFF file"
+    option :help, :aliases => :h, :type => :boolean
+    def build(gff_in)
+  #    puts "build #{gff_file} => #{dbpath}"
+      dbpath = GffDb.build_db(gff_in)
+      STDERR.puts "new database created: #{dbpath}"
+      gff_file = dbpath + "/" + File.basename(gff_in)
+      GffDb.build_tabix(gff_file)
+    end
+
+    desc "search DB QUERY", "search GFF record giving query"
+    option :format, :aliases => :f, :enum => ["json", "gff"], :default => "gff"
+    def search(db, query)
+      ezdb = db
+      files = Dir["#{ezdb}/*.sqlite3"]
+      sq3_file = nil
+      if files.size == 1
+        sq3_file = files[0]
+      elsif files.size == 0
+        raise "sqlite3 file not found"
+      elsif files.size > 1
+        raise "Multiple sqlite3 files found"
+      end
+      sq3_db = GffDb.new(sq3_file)
+      results = sq3_db.search(query, 100)
+      case options[:format]
+      when "json"
+        h = Hash.new
+        ary = results.map{|r| r.to_h}
+        h["gff_records"] = ary
+        puts h.to_json
+      when "gff"
+        gfftxt = results.map{|r| r.to_s}.join("\n")
+        puts CE.pickup(/#{query}/i, :green, nil, :bold).get(gfftxt)
+      else
+        raise "Unknown format: #{options[:format]}"
+      end
+    end
+
+  end
+end
+
+Ezgff::CLI.start(ARGV)
+
+
+

data/ezgff.gemspec

@@ -0,0 +1,30 @@
+require_relative 'lib/ezgff/version'
+
+Gem::Specification.new do |spec|
+  spec.name          = "ezgff"
+  spec.version       = Ezgff::VERSION
+  spec.authors       = ["Shuji Shigenobu"]
+  spec.email         = ["sshigenobu@gmail.com"]
+
+  spec.summary       = %q{Utilities for GFF3}
+  spec.description   = %q{Utilities for GFF3, the genome annotation format. Useful to explore the gene model features.}
+  spec.homepage      = "https://github.com/shujishigenobu/ezgff_alpha"
+  spec.license       = "MIT"
+  spec.required_ruby_version = Gem::Requirement.new(">= 2.3.0")
+
+#  spec.metadata["allowed_push_host"] = "TODO: Set to 'http://mygemserver.com'"
+
+  spec.metadata["homepage_uri"] = spec.homepage
+  spec.metadata["source_code_uri"] = "https://github.com/shujishigenobu/ezgff_alpha"
+  spec.metadata["changelog_uri"] = "https://github.com/shujishigenobu/ezgff_alpha"
+  # TODO: Put your gem's CHANGELOG.md URL here."
+
+  # Specify which files should be added to the gem when it is released.
+  # The `git ls-files -z` loads the files in the RubyGem that have been added into git.
+  spec.files         = Dir.chdir(File.expand_path('..', __FILE__)) do
+    `git ls-files -z`.split("\x0").reject { |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"]
+end

data/lib/ezgff.rb

@@ -0,0 +1,12 @@
+require_relative "ezgff/version"
+require_relative "ezgff/gffsqlitedb"
+
+#require "ezgff/version"
+#require "ezgff/gffsqlitedb"
+
+
+
+module Ezgff
+  class Error < StandardError; end
+  # Your code goes here...
+end

data/lib/ezgff/gffsqlitedb.rb

@@ -0,0 +1,390 @@
+require 'sqlite3'
+require 'json'
+require 'bio'
+require 'fileutils'
+
+#
+# References
+# * Official specification of GFF3 -- https://github.com/The-Sequence-Ontology/Specifications/blob/master/gff3.md
+#
+
+module Ezgff
+
+  class GffDb
+
+    #===
+    # sqlite3 schema
+    #
+    # gff_records (
+    #   line_num     integer primary key,
+    #   record       text,            # original record
+    #   id           text,
+    #   parent       text,
+    #   seqid        text not null,
+    #   source       text,
+    #   type         text,
+    #   start        integer not null,
+    #   end          integer not null,
+    #   score        real,
+    #   strand       varchar(1),
+    #   phase        integer,
+    #   attributes   text,
+    #   attributes_json json
+    # )
+
+    def self.build_db(gff_in, ezdb_base = nil)
+      ezdb_base = (ezdb_base || ".")
+      ezdb_path = ezdb_base + "/" + File.basename(gff_in) + ".ezdb"
+      gff_file = ezdb_path + "/" + File.basename(gff_in)
+      Dir.mkdir(ezdb_path)
+      File.open(gff_file, "w") do |o|
+        File.open(gff_in).each do |l|
+          break if /^\#\#FASTA/.match(l)
+          ## skip header section
+          next if /^\#/.match(l)
+          o.puts l
+        end
+      end
+      
+  #    FileUtils.cp(gff_in, gff_file)
+      sq3_file = gff_file + ".sqlite3"
+
+      ## Create table in sqlite3 RDBMS
+      ##   table name: gff_record
+
+      sq3_db = SQLite3::Database.new(sq3_file)
+
+      sql = <<-SQL
+      CREATE TABLE gff_records (
+        line_num     integer primary key,
+        record       text,
+        id           text,
+        parent       text,
+        seqid        text not null,
+        source       text,
+        type         text,
+        start        integer not null,
+        end          integer not null,
+        score        real,
+        strand       varchar(1),
+        phase        integer,
+        attributes   text,
+        attributes_json json
+      );
+      SQL
+
+      sq3_db.execute(sql)
+
+      ## Read GFF file and insert data into 
+      ## the sqlite3 table
+
+      sq3_db.transaction do 
+        File.open(gff_file).each_with_index do |l, i|
+      #    puts l
+          ## skip FASTA seq section
+          break if /^\#\#FASTA/.match(l)
+      
+          ## skip header section
+          next if /^\#/.match(l)
+          gr = Bio::GFF::GFF3::Record.new(l.chomp)
+      #    p gr.attributes
+          id = nil
+          id_found = gr.attributes.select{|a| a[0] == "ID"}
+          if id_found.size == 1
+            id = id_found[0][1]
+          elsif id_found.size == 0
+            ## do nothing (id = nil)
+          elsif id_found > 1
+            STDERR.puts gr.attributes
+            raise "Multiple IDs found."
+          end
+          parent =  ((gr.attributes.select{|a| a[0] == "Parent"}[0]) || [])[1]
+          a = l.chomp.split(/\t/)
+      
+          sql = "INSERT INTO gff_records (line_num, record, id, parent, seqid, source, type, start, end, score, strand, phase, attributes, attributes_json)
+          VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)"
+          values = [i, l.chomp, id, parent, 
+            a[0], a[1], a[2], a[3], a[4], a[5], a[6], a[7], a[8], 
+            attributes_as_json(l)]
+          sq3_db.execute(sql, values)
+        end
+      end
+
+      ## Indexing the sqlite3 table
+      table = "gff_records"
+      %w{id parent source type}.each do |col|
+        idxname = "index_#{table}_on_#{col}"
+        sql = "CREATE INDEX #{idxname} ON #{table}(#{col})"
+        sq3_db.execute(sql)
+      end
+
+      return ezdb_path
+
+    end
+
+    def self.build_tabix(gff_in)
+      ## sort gff by position
+      gfffile_sorted = gff_in + ".gz"
+      cmd = %Q{(grep ^"#" #{gff_in}; grep -v ^"#" #{gff_in} | sort -t $'\t' -k1,1 -k4,4n) | bgzip > #{gfffile_sorted};}
+      STDERR.puts cmd
+      system cmd
+
+      cmd = "tabix -p gff #{gfffile_sorted}"
+      STDERR.puts cmd
+      system cmd
+      
+      STDERR.puts "#{gfffile_sorted} and #{gfffile_sorted}.tbi were generated."
+    end
+
+    def self.attributes_as_json(gffline)
+      keys_multi_val_allowed = %{Parent Alias Note Dbxref Ontology_term}
+
+      gr = Bio::GFF::GFF3::Record.new(gffline.chomp)
+
+      h = Hash.new
+      gr.attributes.each do |att|
+        k, v = att
+        unless h.has_key?(k)
+          h[k] = []
+        end
+        h[k] << v
+      end
+      h2 = Hash.new
+      h.each do |key, values|
+        if key == "Dbxref" || key == "Ontology_term"
+          h3 = Hash.new
+          values.each do |val|
+            m = /(.+?):/.match(val)
+            dbtag = m[1]
+            dbval = m.post_match
+            h3.update({dbtag => dbval})
+          end
+          h2[key] = h3
+        else
+          h2[key] = values.join(",")
+        end
+      end
+      h2.to_json
+    end
+
+    def initialize(path)
+      @db = SQLite3::Database.new(path)
+    end
+
+    def each_record
+      sql = "SELECT * FROM gff_records"
+      @db.execute(sql).each do |r|
+        an = Annotation.new()
+        an.build_from_db_record(r)
+        yield an
+      end
+    end
+
+    def get(id)
+      sql = %Q{SELECT * FROM gff_records WHERE id=="#{id}";}
+  #    puts sql
+      res = @db.execute(sql)
+      if res.size == 1
+        an = Annotation.new(@db)
+        an.build_from_db_record(res[0])
+        return an
+      else
+        if res.size >= 2
+          raise "multiple hits"
+        elsif res.size == 0
+          raise "not found: #{id}"
+        end
+      end
+    end
+
+    def get_by_line_number(n)
+      sql = %Q{SELECT * FROM gff_records WHERE line_num=="#{n}";}
+      res = @db.execute(sql)
+      if res.size == 1
+        an = Annotation.new(@db)
+        an.build_from_db_record(res[0])
+        return an
+      else
+        if res.size >= 2
+          raise "multiple hits"
+        elsif res.size == 0
+          raise "not found: #{id}"
+        end
+      end
+    end
+
+    def search(query, num_limit=100)
+      sql = %Q{SELECT * FROM  gff_records WHERE id LIKE "%#{query}%" OR parent LIKE "%#{query}%" OR attributes LIKE "%#{query}%";}
+      STDERR.puts sql
+      res = @db.execute(sql)
+      res2 = res.map{|r| an = Annotation.new(@db); an.build_from_db_record(r); an}
+      res2
+    end
+
+    class Annotation
+
+      def initialize(db = nil)
+        @db = db
+        @seqid
+        @source
+        @type
+        @start
+        @end
+        @score
+        @strand
+        @phase
+        @attributes
+        @id
+        @parent_id
+        @gffline
+      end
+
+      attr_accessor :seqid, :source, :type, :start, :end, :score, :strand, :phase, :attributes
+      attr_accessor :id, :parent_id, :gffline, :line_num
+
+      def to_s
+        gffline
+      end
+
+      def to_hash
+        h = {
+          'seqid' => seqid,
+          'source' => source,
+          'type' => type,
+          'start' => start,
+          'end' => self.end,
+          'score' => score,
+          'strand' => strand,
+          'phase' => phase,
+          'line_num' => line_num,
+          'id' => id,
+          'parent_id' => parent_id,
+          'attributes' => attributes
+        }
+      end
+
+      alias :to_h :to_hash
+
+      def to_json
+        self.to_hash.to_json
+      end
+
+      def build_from_db_record(sql_result)
+        ## sql_result: Array returned by @db.execute(sql)
+        v = sql_result
+        @seqid = v[4]
+        @source  = v[5]
+        @type = v[6]
+        @start = v[7]
+        @end = v[8]
+        @score = v[9]
+        @strand = v[10]
+        @phase = v[11]
+        @line_num = v[0]
+        @gffline = v[1]
+        @id = v[2]
+        @parent_id = v[3]
+        @attributes = JSON.parse(v[13])
+      end
+
+      def parent
+        if parent_id
+          sql = %Q{SELECT * FROM gff_records WHERE id=="#{parent_id}";}
+  #        puts sql
+          res = @db.execute(sql)
+          an = Annotation.new(@db)
+          an.build_from_db_record(res[0])
+          return an
+        else
+          return nil
+        end
+      end
+
+      def children
+        ary = []
+        sql = %Q{SELECT * FROM gff_records WHERE parent=="#{id}";}
+  #      puts sql
+        res = @db.execute(sql)
+        res.each do |r|
+          an = Annotation.new(@db)
+          an.build_from_db_record(r)
+          ary << an
+        end
+        ary
+      end
+
+      def descendants
+        ary = []
+        sql = %Q{WITH RECURSIVE r AS (
+          SELECT * FROM gff_records WHERE id=="#{id}"
+          UNION ALL
+          SELECT gff_records.* FROM gff_records, r WHERE gff_records.parent == r.id
+          )
+          SELECT * FROM r}
+        res = @db.execute(sql)
+        res.each do |r|
+          an = Annotation.new(@db)
+          an.build_from_db_record(r)
+          ary << an
+        end
+        ary
+      end
+
+      def ancestors
+        ary = []
+        sql = %Q{WITH RECURSIVE  ancestor AS (
+          SELECT * FROM gff_records WHERE id=="#{id}"
+          UNION ALL
+          SELECT gff_records.* FROM gff_records, ancestor
+          WHERE ancestor.parent = gff_records.id
+          )
+          SELECT * FROM ancestor;}
+        res = @db.execute(sql)
+        res.each do |r|
+          an = Annotation.new(@db)
+          an.build_from_db_record(r)
+          ary << an
+        end
+        ary
+      end
+
+
+      def length
+        len = @end - @start + 1
+        raise unless len > 0
+        return len
+      end
+
+      def dbxrefs
+        h = Hash.new
+        if attributes["Dbxref"]
+          attributes["Dbxref"].split(/,/).each do |x|
+            m = /(.+?):/.match(x)
+            key = m[1]
+            val = m.post_match
+            h.update({key => val})
+          end
+        end
+        h
+      end
+
+    end
+
+  end
+
+end
+
+if __FILE__ == $0
+  dbname = ARGV[0]
+  query = ARGV[1]
+  db = GffDb.new(dbname)
+  ann = db.get(query)
+  p ann
+  puts ann.to_s
+  p ann.to_hash
+  exit
+  db.each_line do |an|
+    p an
+#    p [an.id, an.seqid, an.start, an.end, an.attributes["protein_id"]]
+  end
+end

data/lib/ezgff/version.rb

@@ -0,0 +1,3 @@
+module Ezgff
+  VERSION = "0.0.2"
+end

metadata

@@ -0,0 +1,66 @@
+--- !ruby/object:Gem::Specification
+name: ezgff
+version: !ruby/object:Gem::Version
+  version: 0.0.2
+platform: ruby
+authors:
+- Shuji Shigenobu
+autorequire: 
+bindir: exe
+cert_chain: []
+date: 2021-07-14 00:00:00.000000000 Z
+dependencies: []
+description: Utilities for GFF3, the genome annotation format. Useful to explore the
+  gene model features.
+email:
+- sshigenobu@gmail.com
+executables:
+- ezgff
+extensions: []
+extra_rdoc_files: []
+files:
+- ".gitignore"
+- Gemfile
+- LICENSE
+- README.md
+- Rakefile
+- bin/build_gff_sqlitedb.rb
+- bin/build_gff_sqlitedb_keywords.rb
+- bin/build_gff_tabix.rb
+- dev/gff_examples/ApL_HF_liftover_Refseq.gff.gz
+- dev/gff_examples/ApMT_NC_011594.gb.gff.gz
+- dev/gff_examples/GCF_000009605.1_ASM960v1_genomic.gff.gz
+- dev/gff_examples/apisum_part.gff3.gz
+- dev/gff_examples/ref_pea_aphid_22Mar2018_4r6ur_top_level.chrNamed.gff3.gz
+- exe/ezgff
+- ezgff.gemspec
+- lib/ezgff.rb
+- lib/ezgff/gffsqlitedb.rb
+- lib/ezgff/version.rb
+homepage: https://github.com/shujishigenobu/ezgff_alpha
+licenses:
+- MIT
+metadata:
+  homepage_uri: https://github.com/shujishigenobu/ezgff_alpha
+  source_code_uri: https://github.com/shujishigenobu/ezgff_alpha
+  changelog_uri: https://github.com/shujishigenobu/ezgff_alpha
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: 2.3.0
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubygems_version: 3.1.2
+signing_key: 
+specification_version: 4
+summary: Utilities for GFF3
+test_files: []