sql_to_csv_stream 0.2.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: 69a16996a6f5e332d51e2cf6d352f323a7fe01939d3ff238eec27c1d640958d5
+  data.tar.gz: 8ddc1c3aca1f1d0a70a41af04436c50d4892be178b1991978b8e95bd03d50da6
+SHA512:
+  metadata.gz: 18295c63a869342ab2f1833b968c1374228375fbe7544187c41a68d750de497f67b8659ed44539968f3943df8ff9c7781835ad1475ce142b8d4513651e8ed4e8
+  data.tar.gz: f47042d236d18caa9965d33e7302befd14f14d0c5abb6be343d38ed486e89386890c32955e8836b08575fcb02860f1cbb761a1378ef7a61922140b60be992b8d

data/.circleci/config.yml

@@ -0,0 +1,78 @@
+version: 2
+references:
+  base: &base
+    docker:
+      - image: circleci/ruby:2.6.3
+        environment:
+          RAILS_ENV: test
+          PGHOST: 127.0.0.1
+          PGUSER: bitcrowd
+          DATABASE_URL: "postgres://bitcrowd@localhost:5432/bitcrowd_test"
+          COVERAGE: 'true'
+          BUNDLE_PATH: '~/bitcrowd/vendor/bundle'
+          DISPLAY: 99.0
+          CAPYBARA_WAIT_TIME: 40
+      - image: circleci/postgres:9.6.12-alpine
+        environment:
+          POSTGRES_USER: bitcrowd
+          POSTGRES_DB: bitcrowd_test
+    working_directory: ~/bitcrowd
+jobs:
+  setup:
+    <<: *base
+    steps:
+      - checkout
+
+      # ruby dependencies
+      - restore_cache:
+          keys:
+            - bundler-cache-v1-{{ checksum "Gemfile.lock" }}
+            - bundler-cache-v1-
+      - run: gem install bundler
+      - run:
+          name: Install ruby dependencies
+          command: |
+            bundle check || bundle install --jobs 4 --retry 3
+            bundle clean
+      - save_cache:
+          key: bundler-cache-v1-{{ checksum "Gemfile.lock" }}
+          paths:
+            - vendor/bundle
+
+      - save_cache:
+          key: repo-{{ .Environment.CIRCLE_SHA1 }}
+          paths:
+            - ~/bitcrowd
+  test:
+    <<: *base
+    steps:
+      - restore_cache:
+          key: repo-{{ .Environment.CIRCLE_SHA1 }}
+      - run: 
+          name: Install postgresql-client
+          command: |
+            sudo apt-get update
+            sudo apt install -y postgresql-client
+      - run:
+          name: rubocop
+          command: |
+            bundle exec rubocop
+      - run:
+          name: Wait for DB
+          command: dockerize -wait tcp://localhost:5432 -timeout 1m
+      - run:
+          name: Database Setup
+          command: |
+            bundle exec rails db:create db:schema:load
+      - run:
+          name: rspec
+          command: |
+            bundle exec rspec
+workflows:
+  version: 2
+  checks:
+    jobs:
+      - setup
+      - test:
+          requires:
+            - setup

data/.gitignore

@@ -0,0 +1,16 @@
+/.bundle/
+/.yardoc
+/_yardoc/
+/coverage/
+/doc/
+/pkg/
+/spec/reports/
+/tmp/
+
+# rspec failure tracking
+.rspec_status
+
+# dummy app we only use for testing against rails
+/spec/integration/dummy_app/db
+/spec/integration/dummy_app/tmp
+/spec/integration/dummy_app/log

data/.rspec

@@ -0,0 +1,2 @@
+--color
+--require spec_helper

data/.rubocop.yml

@@ -0,0 +1,18 @@
+require: rubocop-rails
+
+inherit_gem:
+  rubocop-bitcrowd: .rubocop.yml
+
+# Note: skip this if you want to override the default AllCops:Include and AllCops:Exclude list
+inherit_mode:
+  merge:
+    - Include
+    - Exclude
+
+AllCops:
+  Exclude:
+    - 'spec/integration/dummy_app/bin/*'
+    - 'sql_to_csv_stream.gemspec'
+
+Metrics/MethodLength:
+  Max: 15

data/.tool-versions

@@ -0,0 +1 @@
+ruby 2.6.1

data/CHANGELOG.md

@@ -0,0 +1,21 @@
+# SqlToCsvStream Changelog
+
+## 0.4.0 / unreleased
+
+### Features
+
+* 
+
+
+### Bug fixes
+
+* 
+
+
+## 0.2.0 / 2019-08-21
+
+### Security
+
+* upgrade nokogiri (addressed CVE-2019-5477)
+* upgrade all dependent gems
+* move to CircleCI

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 philipp@tessenow.org. 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 +1,8 @@
+# frozen_string_literal: true
+
+source 'https://rubygems.org'
+
+git_source(:github) { |repo_name| "https://github.com/#{repo_name}" }
+
+# Specify your gem's dependencies in sql_to_csv_stream.gemspec
+gemspec

data/Gemfile.lock

@@ -0,0 +1,194 @@
+PATH
+  remote: .
+  specs:
+    sql_to_csv_stream (0.2.0)
+
+GEM
+  remote: https://rubygems.org/
+  specs:
+    actioncable (5.2.3)
+      actionpack (= 5.2.3)
+      nio4r (~> 2.0)
+      websocket-driver (>= 0.6.1)
+    actionmailer (5.2.3)
+      actionpack (= 5.2.3)
+      actionview (= 5.2.3)
+      activejob (= 5.2.3)
+      mail (~> 2.5, >= 2.5.4)
+      rails-dom-testing (~> 2.0)
+    actionpack (5.2.3)
+      actionview (= 5.2.3)
+      activesupport (= 5.2.3)
+      rack (~> 2.0)
+      rack-test (>= 0.6.3)
+      rails-dom-testing (~> 2.0)
+      rails-html-sanitizer (~> 1.0, >= 1.0.2)
+    actionview (5.2.3)
+      activesupport (= 5.2.3)
+      builder (~> 3.1)
+      erubi (~> 1.4)
+      rails-dom-testing (~> 2.0)
+      rails-html-sanitizer (~> 1.0, >= 1.0.3)
+    activejob (5.2.3)
+      activesupport (= 5.2.3)
+      globalid (>= 0.3.6)
+    activemodel (5.2.3)
+      activesupport (= 5.2.3)
+    activerecord (5.2.3)
+      activemodel (= 5.2.3)
+      activesupport (= 5.2.3)
+      arel (>= 9.0)
+    activestorage (5.2.3)
+      actionpack (= 5.2.3)
+      activerecord (= 5.2.3)
+      marcel (~> 0.3.1)
+    activesupport (5.2.3)
+      concurrent-ruby (~> 1.0, >= 1.0.2)
+      i18n (>= 0.7, < 2)
+      minitest (~> 5.1)
+      tzinfo (~> 1.1)
+    addressable (2.6.0)
+      public_suffix (>= 2.0.2, < 4.0)
+    arel (9.0.0)
+    ast (2.4.0)
+    builder (3.2.3)
+    capybara (3.28.0)
+      addressable
+      mini_mime (>= 0.1.3)
+      nokogiri (~> 1.8)
+      rack (>= 1.6.0)
+      rack-test (>= 0.6.3)
+      regexp_parser (~> 1.5)
+      xpath (~> 3.2)
+    coderay (1.1.2)
+    concurrent-ruby (1.1.5)
+    crass (1.0.4)
+    diff-lcs (1.3)
+    erubi (1.8.0)
+    fivemat (1.3.7)
+    globalid (0.4.2)
+      activesupport (>= 4.2.0)
+    i18n (1.6.0)
+      concurrent-ruby (~> 1.0)
+    jaro_winkler (1.5.3)
+    loofah (2.2.3)
+      crass (~> 1.0.2)
+      nokogiri (>= 1.5.9)
+    mail (2.7.1)
+      mini_mime (>= 0.1.1)
+    marcel (0.3.3)
+      mimemagic (~> 0.3.2)
+    method_source (0.9.2)
+    mimemagic (0.3.3)
+    mini_mime (1.0.2)
+    mini_portile2 (2.4.0)
+    minitest (5.11.3)
+    nio4r (2.4.0)
+    nokogiri (1.10.4)
+      mini_portile2 (~> 2.4.0)
+    parallel (1.17.0)
+    parser (2.6.3.0)
+      ast (~> 2.4.0)
+    pg (1.1.4)
+    pry (0.12.2)
+      coderay (~> 1.1.0)
+      method_source (~> 0.9.0)
+    pry-rails (0.3.9)
+      pry (>= 0.10.4)
+    public_suffix (3.1.1)
+    puma (3.12.1)
+    rack (2.0.7)
+    rack-test (1.1.0)
+      rack (>= 1.0, < 3)
+    rails (5.2.3)
+      actioncable (= 5.2.3)
+      actionmailer (= 5.2.3)
+      actionpack (= 5.2.3)
+      actionview (= 5.2.3)
+      activejob (= 5.2.3)
+      activemodel (= 5.2.3)
+      activerecord (= 5.2.3)
+      activestorage (= 5.2.3)
+      activesupport (= 5.2.3)
+      bundler (>= 1.3.0)
+      railties (= 5.2.3)
+      sprockets-rails (>= 2.0.0)
+    rails-dom-testing (2.0.3)
+      activesupport (>= 4.2.0)
+      nokogiri (>= 1.6)
+    rails-html-sanitizer (1.2.0)
+      loofah (~> 2.2, >= 2.2.2)
+    railties (5.2.3)
+      actionpack (= 5.2.3)
+      activesupport (= 5.2.3)
+      method_source
+      rake (>= 0.8.7)
+      thor (>= 0.19.0, < 2.0)
+    rainbow (3.0.0)
+    rake (10.5.0)
+    regexp_parser (1.6.0)
+    rspec (3.8.0)
+      rspec-core (~> 3.8.0)
+      rspec-expectations (~> 3.8.0)
+      rspec-mocks (~> 3.8.0)
+    rspec-core (3.8.2)
+      rspec-support (~> 3.8.0)
+    rspec-expectations (3.8.4)
+      diff-lcs (>= 1.2.0, < 2.0)
+      rspec-support (~> 3.8.0)
+    rspec-mocks (3.8.1)
+      diff-lcs (>= 1.2.0, < 2.0)
+      rspec-support (~> 3.8.0)
+    rspec-support (3.8.2)
+    rubocop (0.74.0)
+      jaro_winkler (~> 1.5.1)
+      parallel (~> 1.10)
+      parser (>= 2.6)
+      rainbow (>= 2.2.2, < 4.0)
+      ruby-progressbar (~> 1.7)
+      unicode-display_width (>= 1.4.0, < 1.7)
+    rubocop-bitcrowd (1.3.0)
+      rubocop (~> 0.56)
+    rubocop-rails (2.3.0)
+      rack (>= 1.1)
+      rubocop (>= 0.72.0)
+    ruby-progressbar (1.10.1)
+    sprockets (3.7.2)
+      concurrent-ruby (~> 1.0)
+      rack (> 1, < 3)
+    sprockets-rails (3.2.1)
+      actionpack (>= 4.0)
+      activesupport (>= 4.0)
+      sprockets (>= 3.0.0)
+    thor (0.20.3)
+    thread_safe (0.3.6)
+    tzinfo (1.2.5)
+      thread_safe (~> 0.1)
+    unicode-display_width (1.6.0)
+    websocket-driver (0.7.1)
+      websocket-extensions (>= 0.1.0)
+    websocket-extensions (0.1.4)
+    xpath (3.2.0)
+      nokogiri (~> 1.8)
+
+PLATFORMS
+  ruby
+
+DEPENDENCIES
+  bundler (~> 1.17)
+  capybara
+  fivemat
+  pg
+  pry
+  pry-rails
+  puma (~> 3.11)
+  rails (~> 5.2.2)
+  rake (~> 10.0)
+  rspec (~> 3.0)
+  rubocop
+  rubocop-bitcrowd
+  rubocop-rails
+  sql_to_csv_stream!
+
+BUNDLED WITH
+   1.17.3

data/LICENSE.txt

@@ -0,0 +1,21 @@
+The MIT License (MIT)
+
+Copyright (c) 2019 Philipp Tessenow
+
+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 +1,120 @@
+# SqlToCsvStream
+
+This is your favorite gem to produce CSV or JSON directly from SQL queries.
+It queries a PostgreSQL with a [`COPY`](https://www.postgresql.org/docs/current/sql-copy.html) statement and streams the result as CSV/JSON directly into a ruby enumerator.
+
+This gem can be used in all ruby applications, but ships with a special renderer for Rails to easily render downloads from your rails controller.
+
+Note: This is project is still in a proof-of-concept phase. We may rename some things, make the code more readable and very likely add some tests :)
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+```ruby
+gem 'sql_to_csv_stream'
+```
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install sql_to_csv_stream
+
+If you use rails, you may register the new stream renderers in an initializer.
+
+```ruby
+require 'sql_to_csv_stream'
+
+SqlToCsvStream.register_rails_renderer
+```
+
+## Usage
+
+In Rails, you can use the stream renderer from a Controller:
+
+```ruby
+class UsersController < ApplicationController
+  def index
+    @users = User.all.where(deleted_at: null)
+
+    respond_to do |format|
+      format.csv do
+        render csv_stream: @users, filename: 'users.csv'
+      end
+      format.json do
+        render json_stream: @users, filename: 'users.json'
+      end
+    end
+  end
+end
+```
+
+This, unlike many other CSV/JSON rendering techniques, instantly sends results to the user by streaming the content while it is being generated.
+This is light on memory. By streaming the data instantly, even large files (that need longer to generate than the HTTP server connection timeout value) can be produced without the connection being interrupted by a connection timeout.
+
+The streaming renderer automatically responds with a gzipped encoding if the client accepts it. This drastically reduces file sizes we need to send over the wire.
+
+Any SQL string the PostgreSQL [`COPY` command](https://www.postgresql.org/docs/current/sql-copy.html) accepts can be given to the renderer.
+Alternatively, any object may be given that produces such SQL on `.to_sql` or `to_s`.
+So you can use your favorite query-object pattern :)
+
+If you are not in Rails or want to process CSV/JSON in any other way from within Rails, you can use the `*Enumerator` classes.
+
+```ruby
+file = File.open('users.csv', 'w')
+SqlToCsvStream::CsvEnumerator.new('SELECT * FROM users;').each do |csv_row|
+  file.write
+end
+file.close
+```
+
+Or write the compressed file with:
+
+```ruby
+csv_enum = SqlToCsvStream::CsvEnumerator.new('SELECT * FROM users;')
+zip_enum = SqlToCsvStream::GzipWrapper.new(csv_enum)
+
+file = File.open('users.csv.gz', 'w')
+zip_enum.each do |csv_row|
+  file.write
+end
+file.close
+```
+
+Writing a JSON file works similarly:
+
+```ruby
+file = File.open('users.json', 'w')
+SqlToCsvStream::JsonEnumerator.new('SELECT * FROM users;').each do |csv_row|
+  file.write
+end
+file.close
+```
+
+For more options, see the class documentation of the `CsvEnumerator` or `JsonEnumerator` class.
+
+## 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/tessi/sql_to_csv_stream. New feature ideas are welcome too -- please present your ideas in an issue first so we can together discuss whether this idea fits into the scope of this project.
+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.
+
+## License
+
+The gem is available as open source under the terms of the [MIT License](https://opensource.org/licenses/MIT).
+
+## Code of Conduct
+
+Everyone interacting in the SqlToCsvStream project’s codebases, issue trackers, chat rooms and mailing lists is expected to follow the [code of conduct](https://github.com/tessi/sql_to_csv_stream/blob/master/CODE_OF_CONDUCT.md).
+
+## Previous work
+
+We didn't invent streaming, nor did we were the first to have the idea to integrate this in ruby and/or rails. Some previous approaches are described [here](https://shift.infinite.red/fast-csv-report-generation-with-postgres-in-rails-d444d9b915ab), [here](https://www.smartly.io/blog/streaming-data-with-ruby-enumerators), [here](https://medium.com/table-xi/stream-csv-files-in-rails-because-you-can-46c212159ab7), or [here](https://gist.github.com/stereoscott/6996507). We are thankful for the previous work done which led us into the right direction and enabled us to (hopefully) improve upon it.

data/Rakefile

@@ -0,0 +1,8 @@
+# frozen_string_literal: true
+
+require 'bundler/gem_tasks'
+require 'rspec/core/rake_task'
+
+RSpec::Core::RakeTask.new(:spec)
+
+task default: :spec

data/bin/console

@@ -0,0 +1,15 @@
+#!/usr/bin/env ruby
+# frozen_string_literal: true
+
+require 'bundler/setup'
+require 'sql_to_csv_stream'
+
+# 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/lib/sql_to_csv_stream.rb

@@ -0,0 +1,14 @@
+# frozen_string_literal: true
+
+require 'sql_to_csv_stream/version'
+require 'sql_to_csv_stream/gzip_wrapper'
+require 'sql_to_csv_stream/postgresql_copy_enumerator'
+require 'sql_to_csv_stream/csv_enumerator'
+require 'sql_to_csv_stream/json_enumerator'
+require 'sql_to_csv_stream/rails_support'
+
+module SqlToCsvStream
+  def self.register_rails_renderer
+    RailsSupport.register_renderer
+  end
+end

data/lib/sql_to_csv_stream/csv_enumerator.rb

@@ -0,0 +1,58 @@
+# frozen_string_literal: true
+
+require 'csv'
+
+module SqlToCsvStream
+  class CsvEnumerator
+    PREFIXES_TO_ESCAPE = %w[= @ + - |].freeze
+    ESCAPE_CHAR = "'"
+
+    # Other possible options are
+    #   force_quote: '*'
+    #   escape: "E'\\\\'"
+    # For details see Postgresqls COPY documentation.
+    COPY_OPTIONS_DEFAULTS = {
+      format: 'CSV',
+      header: true
+    }.freeze
+
+    def initialize(
+      object,
+      connection: PostgresqlCopyEnumerator.default_connection,
+      copy_options: {},
+      sanitize: true,
+      force_quotes: false
+    )
+      @sanitize = sanitize
+      @force_quotes = force_quotes
+
+      sql = (object.respond_to?(:to_sql) ? object.to_sql : object.to_s).chomp(';')
+      copy_options = COPY_OPTIONS_DEFAULTS.merge(copy_options)
+      copy_options[:force_quote] = '*' if @force_quotes
+      @copy_enum = PostgresqlCopyEnumerator.new(sql, connection: connection, copy_options: copy_options)
+    end
+
+    def each
+      @copy_enum.each do |line|
+        yield(sanitize(line)) if block_given?
+      end
+    end
+
+    private
+
+    def sanitize(line)
+      return line unless @sanitize
+
+      row = CSV.parse_line(line, headers: false)
+               .map do |value|
+                 if value.to_s.start_with?(*PREFIXES_TO_ESCAPE)
+                   ESCAPE_CHAR + value
+                 else
+                   value
+                 end
+               end
+
+      CSV.generate_line(row, headers: false, force_quotes: @force_quotes)
+    end
+  end
+end

data/lib/sql_to_csv_stream/gzip_wrapper.rb

@@ -0,0 +1,29 @@
+# frozen_string_literal: true
+
+require 'zlib'
+
+module SqlToCsvStream
+  class GzipWrapper
+    def initialize(source)
+      @source = source
+    end
+
+    def each(&block)
+      @destination = block
+      # Zlib::GzipWriter needs to get passed an object that implements the #write method.
+      # this is why we implement the #write method further down
+      # while assigning the stream we need to write to in an instance variable to be used there.
+      @zipper = Zlib::GzipWriter.new(self)
+      @source.each do |string|
+        @zipper.write(string)
+      end
+    ensure
+      @zipper.close
+    end
+
+    # called indirectly by Zlib::GzipWriter
+    def write(zipped_string)
+      @destination.yield(zipped_string)
+    end
+  end
+end

data/lib/sql_to_csv_stream/json_enumerator.rb

@@ -0,0 +1,36 @@
+# frozen_string_literal: true
+
+module SqlToCsvStream
+  class JsonEnumerator
+    JSON_COPY_OPTIONS = { format: 'TEXT' }.freeze
+
+    def initialize(object, connection: PostgresqlCopyEnumerator.default_connection)
+      sql = (object.respond_to?(:to_sql) ? object.to_sql : object.to_s).chomp(';')
+      # The inspiration of this magic was:
+      # https://dba.stackexchange.com/questions/90482/export-postgres-table-as-json?newreg=0b667caa47c34084bee6c90feec5e4be
+      #
+      # The idea is to stream with postgresql COPY command with the TEXT format.
+      # To do this, we need to convert each row in the postgresql query result into JSON first.
+      # This query does exactly that by using ROW_TO_JSON.
+      # There is one edge case when text in that JSON contains backslashes -- to not break our
+      # escaping, we need to manually add additional escape-backslashes.
+      sql = "SELECT REGEXP_REPLACE(ROW_TO_JSON(t)::TEXT, '\\\\', '\\', 'g') FROM (#{sql}) AS t"
+      @copy_enum = PostgresqlCopyEnumerator.new(sql, connection: connection, copy_options: JSON_COPY_OPTIONS)
+    end
+
+    def each(&stream)
+      stream.yield('[')
+
+      # do not prepend a comma on the very first item
+      # to not break json syntax
+      prepend_comma = false
+      @copy_enum.each do |line|
+        line = ',' + line if prepend_comma
+        prepend_comma = true
+        stream.yield(line.chomp)
+      end
+
+      stream.yield("]\n")
+    end
+  end
+end

data/lib/sql_to_csv_stream/postgresql_copy_enumerator.rb

@@ -0,0 +1,40 @@
+# frozen_string_literal: true
+
+module SqlToCsvStream
+  class PostgresqlCopyEnumerator
+    COPY_OPTIONS_DEFAULTS = {
+      encoding: 'utf8'
+    }.freeze
+
+    def self.default_connection
+      raise 'PostgreSQL database connection required' unless defined?(ActiveRecord)
+
+      ActiveRecord::Base.connection.raw_connection
+    end
+
+    def initialize(sql, connection: self.class.default_connection, copy_options: {})
+      @sql = sql.chomp(';')
+      @connection = connection
+      @copy_options = COPY_OPTIONS_DEFAULTS.merge(copy_options)
+    end
+
+    def each
+      @connection.copy_data(copy_sql) do
+        while (row = @connection.get_copy_data)
+          yield(row) if block_given?
+        end
+      end
+    end
+
+    private
+
+    def copy_sql
+      "COPY (#{@sql}) TO STDOUT WITH (#{joined_copy_options})"
+    end
+
+    def joined_copy_options
+      @copy_options.map { |k, v| "#{k.upcase} #{v}" }
+                   .join(', ')
+    end
+  end
+end

data/lib/sql_to_csv_stream/rails_support.rb

@@ -0,0 +1,57 @@
+# frozen_string_literal: true
+
+module SqlToCsvStream
+  module RailsSupport
+    def self.register_renderer
+      register_csv_renderer
+      register_json_renderer
+    end
+
+    # `stream` can be anything that responds to `.each`.
+    # We make use of this by providing our own stream that fetches data from Postgresql
+    # stream = (1..10).lazy.map do |i|
+    #   sleep(1);
+    #   "#{i}\n";
+    # end
+    # stream = Enumerator.new do |strean|
+    #   csv_service.call do |csv_line|
+    #     strean << csv_line
+    #   end
+    # end
+    def self.register_csv_renderer
+      ActionController::Renderers.add :csv_stream do |sql, copy_options: {}, **options|
+        sanitize = options.delete(:sanitize) || true
+        force_quotes = options.delete(:force_quotes) || false
+        filename = options.delete(:filename) || 'data.csv'
+        stream = CsvEnumerator.new(sql, copy_options: copy_options, sanitize: sanitize, force_quotes: force_quotes)
+        stream = GzipWrapper.new(stream) if RailsSupport.use_gzip?(request)
+        RailsSupport.set_streaming_headers(headers, request, response, filename)
+        stream
+      end
+    end
+
+    def self.register_json_renderer
+      ActionController::Renderers.add :json_stream do |sql, filename: 'data.csv'|
+        stream = JsonEnumerator.new(sql)
+        stream = GzipWrapper.new(stream) if RailsSupport.use_gzip?(request)
+        RailsSupport.set_streaming_headers(headers, request, response, filename)
+        stream
+      end
+    end
+
+    def self.set_streaming_headers(headers, request, response, filename)
+      headers['X-Accel-Buffering'] = 'no'
+      headers['Cache-Control'] = 'no-cache'
+      headers['Content-Encoding'] = 'gzip' if use_gzip?(request)
+      headers['Content-Disposition'] = "attachment; filename=\"#{filename}\""
+      headers.delete('Content-Length')
+      response.status = 200
+    end
+
+    def self.use_gzip?(request)
+      request.headers['HTTP_ACCEPT_ENCODING']
+             .to_s
+             .include?('gzip')
+    end
+  end
+end

data/lib/sql_to_csv_stream/version.rb

@@ -0,0 +1,5 @@
+# frozen_string_literal: true
+
+module SqlToCsvStream
+  VERSION = '0.2.0'
+end

data/sql_to_csv_stream.gemspec

@@ -0,0 +1,51 @@
+# frozen_string_literal: true
+
+lib = File.expand_path('lib', __dir__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require 'sql_to_csv_stream/version'
+
+Gem::Specification.new do |spec|
+  spec.name          = 'sql_to_csv_stream'
+  spec.version       = SqlToCsvStream::VERSION
+  spec.authors       = ['Philipp Tessenow']
+  spec.email         = ['philipp@tessenow.org']
+
+  spec.summary       = 'A shortcut to the COPY command from PostgreSQL. Give it SQL and get an Enumerator for the CSV that comes out of it.'
+  spec.description   = 'A shortcut to the COPY command from PostgreSQL. Give it SQL and get an Enumerator for the CSV that comes out of it.'
+  spec.homepage      = 'https://github.com/tessi/sql_to_csv_stream'
+  spec.license       = 'MIT'
+
+  if spec.respond_to?(:metadata)
+    spec.metadata['homepage_uri'] = spec.homepage
+    spec.metadata['source_code_uri'] = 'https://github.com/tessi/sql_to_csv_stream'
+    spec.metadata['changelog_uri'] = 'https://github.com/tessi/sql_to_csv_stream/master/CHANGELOG.md'
+  else
+    raise 'RubyGems 2.0 or newer is required to protect against ' \
+      'public gem pushes.'
+  end
+
+  # 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(__dir__)) 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']
+
+  spec.add_development_dependency 'bundler', '~> 1.17'
+  spec.add_development_dependency 'pry'
+  spec.add_development_dependency 'rake', '~> 10.0'
+  spec.add_development_dependency 'rspec', '~> 3.0'
+  spec.add_development_dependency 'fivemat'
+
+  # for the rails dummy app
+  spec.add_development_dependency 'capybara'
+  spec.add_development_dependency 'pg'
+  spec.add_development_dependency 'pry-rails'
+  spec.add_development_dependency 'puma', '~> 3.11'
+  spec.add_development_dependency 'rails', '~> 5.2.2'
+  spec.add_development_dependency 'rubocop'
+  spec.add_development_dependency 'rubocop-bitcrowd'
+  spec.add_development_dependency 'rubocop-rails'
+end

metadata

@@ -0,0 +1,252 @@
+--- !ruby/object:Gem::Specification
+name: sql_to_csv_stream
+version: !ruby/object:Gem::Version
+  version: 0.2.0
+platform: ruby
+authors:
+- Philipp Tessenow
+autorequire: 
+bindir: exe
+cert_chain: []
+date: 2019-08-21 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.17'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.17'
+- !ruby/object:Gem::Dependency
+  name: pry
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !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'
+- !ruby/object:Gem::Dependency
+  name: fivemat
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: capybara
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: pg
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: pry-rails
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: puma
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.11'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.11'
+- !ruby/object:Gem::Dependency
+  name: rails
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 5.2.2
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 5.2.2
+- !ruby/object:Gem::Dependency
+  name: rubocop
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: rubocop-bitcrowd
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: rubocop-rails
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+description: A shortcut to the COPY command from PostgreSQL. Give it SQL and get an
+  Enumerator for the CSV that comes out of it.
+email:
+- philipp@tessenow.org
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- ".circleci/config.yml"
+- ".gitignore"
+- ".rspec"
+- ".rubocop.yml"
+- ".tool-versions"
+- CHANGELOG.md
+- CODE_OF_CONDUCT.md
+- Gemfile
+- Gemfile.lock
+- LICENSE.txt
+- README.md
+- Rakefile
+- bin/console
+- bin/setup
+- lib/sql_to_csv_stream.rb
+- lib/sql_to_csv_stream/csv_enumerator.rb
+- lib/sql_to_csv_stream/gzip_wrapper.rb
+- lib/sql_to_csv_stream/json_enumerator.rb
+- lib/sql_to_csv_stream/postgresql_copy_enumerator.rb
+- lib/sql_to_csv_stream/rails_support.rb
+- lib/sql_to_csv_stream/version.rb
+- sql_to_csv_stream.gemspec
+homepage: https://github.com/tessi/sql_to_csv_stream
+licenses:
+- MIT
+metadata:
+  homepage_uri: https://github.com/tessi/sql_to_csv_stream
+  source_code_uri: https://github.com/tessi/sql_to_csv_stream
+  changelog_uri: https://github.com/tessi/sql_to_csv_stream/master/CHANGELOG.md
+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: []
+rubygems_version: 3.0.2
+signing_key: 
+specification_version: 4
+summary: A shortcut to the COPY command from PostgreSQL. Give it SQL and get an Enumerator
+  for the CSV that comes out of it.
+test_files: []