csv_tools 0.1.1

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 90e76e93fa5688fed25b5c7870d318929bfc505e
+  data.tar.gz: 544f99192cddc9152eb8787844688ac6844acc79
+SHA512:
+  metadata.gz: 5a350262ab443cdbe23a7f1cd8c80a51187471f116da264d1571b9bf5bc529eb2891b7082913c48fcbacee4a116d7befd3646d8da39ef2b6e64e23500e6c5c38
+  data.tar.gz: 123b2e8424f7d6a169f2c775cd6e07c4749bca58d37ab6a3e95e5e9781420639da5eed9998fc70cdad963a4d4b42ee0d257e38bc1338a10f2d25eab5a2b4df78

data/.gitignore

@@ -0,0 +1,9 @@
+/.bundle/
+/.yardoc
+/Gemfile.lock
+/_yardoc/
+/coverage/
+/doc/
+/pkg/
+/spec/reports/
+/tmp/

data/Gemfile

@@ -0,0 +1,4 @@
+source 'https://rubygems.org'
+
+# Specify your gem's dependencies in csv_tools.gemspec
+gemspec

data/LICENSE.txt

@@ -0,0 +1,21 @@
+The MIT License (MIT)
+
+Copyright (c) 2015 Joey Freund
+
+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 +1,73 @@
+# CSV Tools
+
+A simple utility library and scripts to perform simple operations on CSV files.
+At the moment, the following operations are supported:
+
+ * Selecting specific columns (by index)
+ * Filter rows, based on a specific field
+ * Join two CSV files on a single column
+
+## Installation
+
+```
+gem install csv_tools
+```
+
+## Examples
+
+Using the following data files
+
+```sh
+$ cat students.csv
+student-id,name
+1,Alice
+2,Bob
+3,Rob
+4,Allie
+
+$ cat marks.csv
+student-id,Assignment 1,Assignment 2,Test
+1,72,83,77
+2,53,61,58
+3,85,88,87
+4,92,80,75
+```
+
+#### Select
+
+Select specific columns, by index.
+
+```sh
+$ csv_select marks.csv 0 3
+student-id,Test
+1,77
+2,58
+3,87
+4,75
+```
+
+#### Join
+
+Join two files on a column (called `student-id`)
+
+```sh
+$ csv_join students.csv marks.csv student-id
+student-id,name,Assignment 1,Assignment 2,Test
+1,Alice,72,83,77
+2,Bob,53,61,58
+3,Rob,85,88,87
+4,Allie,92,80,75
+```
+
+#### Filter
+
+Keep rows whose second column (i.e. at index 1) contains the string `ob`
+
+```sh
+$ csv_join students.csv marks.csv student-id > joined.csv
+
+$ csv_filter joined.csv 1 ob
+student-id,name,Assignment 1,Assignment 2,Test
+2,Bob,53,61,58
+3,Rob,85,88,87
+```

data/Rakefile

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

data/bin/csv_filter

@@ -0,0 +1,11 @@
+#!/usr/bin/env ruby
+
+require 'csv_tools'
+
+if ARGV.length != 3
+  abort("Usage: #{File.basename($0)} CSV-FILE COLUMN-INDEX FIELD-VALUE")
+end
+
+column_index = ARGV[1].to_i
+raise "Invalid index #{ARGV[1]}" if column_index.nil?
+CSVTools::csv_filter(ARGV[0], column_index, ARGV[2])

data/bin/csv_join

@@ -0,0 +1,10 @@
+#!/usr/bin/env ruby
+
+require 'csv_tools'
+
+
+if ARGV.length != 3
+  abort("Usage: #{File.basename($0)} CSV-FILE1 CSV-FILE2 JOIN-BY-COLUMN")
+end
+
+CSVTools::csv_join(ARGV[0], ARGV[1], ARGV[2])

data/bin/csv_select

@@ -0,0 +1,11 @@
+#!/usr/bin/env ruby
+
+require 'csv_tools'
+
+if ARGV.length < 3
+  abort("Usage: #{File.basename($0)} CSV-FILE COLUMN-INDEX [COLUMN-INDEX ...]")
+end
+
+indices = ARGV[1..-1].map {|s| s.to_i}
+raise "Invalid indices #{ARGV[1..-1]}" if indices.any? {|i| i.nil?}
+CSVTools::csv_select(ARGV[0], indices)

data/csv_tools.gemspec

@@ -0,0 +1,24 @@
+# coding: utf-8
+lib = File.expand_path('../lib', __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require 'csv_tools/version'
+
+Gem::Specification.new do |spec|
+  spec.name          = "csv_tools"
+  spec.version       = CSVTools::VERSION
+  spec.authors       = ["Joey Freund"]
+  spec.email         = ["joeyfreund@gmail.com"]
+
+  spec.summary       = %q{Command-line tools for CSV file manipulation.}
+  spec.description   = %q{Manipulate CSV files as if they were SQL tables.}
+  spec.homepage      = "https://github.com/joeyfreund/csv_tools"
+  spec.license       = "MIT"
+
+  spec.files         = `git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(test|spec|features)/}) }
+  spec.bindir        = "bin"
+  spec.executables   = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
+  spec.require_paths = ["lib"]
+
+  spec.add_development_dependency "bundler", "~> 1.10"
+  spec.add_development_dependency "rake", "~> 10.0"
+end

data/lib/csv_tools/version.rb

@@ -0,0 +1,3 @@
+module CSVTools
+  VERSION = "0.1.1"
+end

data/lib/csv_tools.rb

@@ -0,0 +1,91 @@
+require 'csv'
+require 'set'
+require "csv_tools/version"
+
+
+
+module CSVTools
+
+
+  DEFAULT_CSV_READ_OPTS = {headers: true, skip_blanks: true}
+
+
+  # @param csv_table [CSV::Table]
+  # @param column_index [integer]
+  # @return Hash[string --> Array of string-arrays]
+  def CSVTools.group_by_column(csv_table, column_index)
+    result = {}
+
+    csv_table.group_by {|row| row.fields[column_index]} .each do |key, row_objects|
+      result[key] = row_objects.map  do |row|
+        row.fields[0...column_index] + row.fields[column_index + 1...row.fields.length]
+      end
+    end
+
+    return result
+  end
+
+
+
+
+  def CSVTools.csv_join(path1, path2, join_by_column, out = STDOUT)
+    csv1, csv2 = [path1, path2].map {|p| CSV.read(p, DEFAULT_CSV_READ_OPTS)}
+
+    # Make sure the join-by column exists in both CSV's
+    index1, index2 = [csv1, csv2].map {|csv| csv.headers.index(join_by_column) }
+    raise "#{path1} does not have a column '#{join_by_column}'" if index1.nil?
+    raise "#{path2} does not have a column '#{join_by_column}'" if index2.nil?
+
+    # Print the header line (join-by column is first, and appears only once)
+    h1, h2 = [csv1.headers , csv2.headers]
+    h1.delete_at(index1)
+    h2.delete_at(index2)
+    out.puts join_by_column + ',' + h1.join(",") + ',' + h2.join(',')
+
+    # Print the data rows ...
+    hash1 = group_by_column(csv1, index1)
+    hash2 = group_by_column(csv2, index2)
+
+    # And now ... JOIN the two CSV's (adding nil's for missing rows)
+    (hash1.keys + hash2.keys).to_set.each do |key|
+      rows1 = hash1[key] || [ [nil] * (csv1.headers.length - 1)]
+      rows2 = hash2[key] || [ [nil] * (csv2.headers.length - 1)]
+
+      rows1.each do |r1|
+        rows2.each do |r2|
+          out.puts key + ',' + r1.join(',') + ',' + r2.join(',')
+        end
+      end
+    end
+
+  end
+
+
+
+
+  def CSVTools.select_values(values, indices)
+    raise "Invalid indices #{indices} for #{values}" if indices.any? {|i| i < 0 || i >= values.length}
+    return indices.map {|i| values[i]}
+  end
+
+
+  def CSVTools.csv_select(path, column_indices, out = STDOUT)
+    csv = CSV.read(path, DEFAULT_CSV_READ_OPTS)
+
+    out.puts select_values(csv.headers, column_indices).join(',')
+    csv.each do |row|
+      out.puts select_values(row.fields, column_indices).join(',')
+    end
+  end
+
+
+  def CSVTools.csv_filter(path, column_index, field_value, out = STDOUT)
+    csv = CSV.read(path, DEFAULT_CSV_READ_OPTS)
+
+    out.puts csv.headers.join(',')
+    csv.select {|row| row.fields[column_index].downcase.include? field_value.downcase} .each do |row|
+      out.puts row.fields.join(',')
+    end
+  end
+
+end

metadata

@@ -0,0 +1,86 @@
+--- !ruby/object:Gem::Specification
+name: csv_tools
+version: !ruby/object:Gem::Version
+  version: 0.1.1
+platform: ruby
+authors:
+- Joey Freund
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2015-12-13 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.10'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.10'
+- !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'
+description: Manipulate CSV files as if they were SQL tables.
+email:
+- joeyfreund@gmail.com
+executables:
+- csv_filter
+- csv_join
+- csv_select
+extensions: []
+extra_rdoc_files: []
+files:
+- ".gitignore"
+- Gemfile
+- LICENSE.txt
+- README.md
+- Rakefile
+- bin/csv_filter
+- bin/csv_join
+- bin/csv_select
+- csv_tools.gemspec
+- lib/csv_tools.rb
+- lib/csv_tools/version.rb
+homepage: https://github.com/joeyfreund/csv_tools
+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: 2.4.8
+signing_key: 
+specification_version: 4
+summary: Command-line tools for CSV file manipulation.
+test_files: []