PoParser 2.0.1 → 3.0.0

data/test/benchmark_small.po

@@ -0,0 +1,46 @@
+# PO benchmark file header
+#
+#, fuzzy
+msgid ""
+msgstr ""
+"Content-Type: text/plain; charset=UTF-8\n"
+"Content-Transfer-Encoding: 8bit\n"
+
+#: m
+msgctxt "AESMM"
+msgid "QtXRl"
+msgid_plural "h"
+msgstr[0] "spfQ9g"
+msgstr[1] "spfQ9g"
+
+# EnfA
+#: EnthqvU2qf6kF
+msgctxt "9ihYCwlIEg=="
+msgid "AloClNt81srB2Op/gEoKap7QvzlMzWBXxMEWLyjI2bQZV3praFAT2jpYhfQmgzu4Wix2tAsOeZV6lZ1TcnRmuHXht8FLfE016Q=="
+msgstr "i+9eqs/otjcsICeBK5MEcfQ5hJOmP++ROezIMcPEWVOEh+XAT1brUoxfqrQAMefK"
+
+#: jg4iou6yRTCJ7XNHeEqikz
+msgctxt "9dPrCW63vhWJwoO"
+msgid ""
+"ZPcE\n"
+"llqi4\n"
+msgstr ""
+"sKNQc\n"
+"BwQ\n"
+
+#: Ld
+#, fuzzy
+#| msgctxt "M6J"
+#| msgid "P4"
+msgctxt "MA9k"
+msgid "P4Zc"
+msgstr "4ZcKx"
+
+#: g3K
+#~ msgctxt "CVdDY"
+#~ msgid ""
+#~ "8Jw\n"
+#~ "dwtm\n"
+#~ msgstr ""
+#~ "KNV2\n"
+#~ "lEWV\n"

data/test/complex_entry.po

@@ -0,0 +1,21 @@
+# translator-comment
+#
+#. extract
+#: reference1
+#: reference2
+#, flag
+#| msgctxt "previous context"
+#| msgid ""
+#|  "multiline\n"
+#|"previous messageid"
+#| msgid_plural "previous msgid_plural"
+msgctxt "Context"
+msgid "msgid"
+msgid_plural ""
+"multiline msgid_plural\n"
+""
+msgstr[0] "msgstr 0"
+msgstr[1] ""
+"msgstr 1 multiline 1\n"
+"msgstr 1 line 2\n"
+msgstr[2] "msgstr 2"

data/test/escape_string.txt

@@ -0,0 +1,7 @@
+This \" is a string with escaped \" and also escaped \\\\ and a lot of them \\\\\\\\\" bla\\" blub'  
+
+We also have a second line with text
+
+
+
+ We also have a second line

metadata

@@ -1,29 +1,29 @@
 --- !ruby/object:Gem::Specification
 name: PoParser
 version: !ruby/object:Gem::Version
-  version: 2.0.1
+  version: 3.0.0
 platform: ruby
 authors:
 - Arash Mousavi
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2016-12-29 00:00:00.000000000 Z
+date: 2017-05-23 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
-  name: parslet
+  name: simple_po_parser
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '1.7'
+        version: '1.1'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '1.7'
+        version: '1.1'
 - !ruby/object:Gem::Dependency
   name: bundler
   requirement: !ruby/object:Gem::Requirement
@@ -75,10 +75,8 @@ files:
 - lib/poparser/entry.rb
 - lib/poparser/header.rb
 - lib/poparser/message.rb
-- lib/poparser/parser.rb
 - lib/poparser/po.rb
 - lib/poparser/tokenizer.rb
-- lib/poparser/transformer.rb
 - lib/poparser/version.rb
 - poparser.gemspec
 - spec/poparser/comment_spec.rb
@@ -92,12 +90,15 @@ files:
 - spec/poparser/fixtures/tokenizer_empty_line.po
 - spec/poparser/header_spec.rb
 - spec/poparser/message_spec.rb
-- spec/poparser/parser_spec.rb
 - spec/poparser/po_spec.rb
 - spec/poparser/poparser_spec.rb
 - spec/poparser/tokenizer_spec.rb
-- spec/poparser/transformer_spec.rb
 - spec/spec_helper.rb
+- spec/utils/random_pofile_generator.rb
+- test/benchmark.po
+- test/benchmark_small.po
+- test/complex_entry.po
+- test/escape_string.txt
 homepage: http://github.com/arashm/poparser
 licenses:
 - MIT
@@ -118,7 +119,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 2.6.8
+rubygems_version: 2.6.12
 signing_key: 
 specification_version: 4
 summary: A PO file parser, editor and generator.
@@ -134,9 +135,8 @@ test_files:
 - spec/poparser/fixtures/tokenizer_empty_line.po
 - spec/poparser/header_spec.rb
 - spec/poparser/message_spec.rb
-- spec/poparser/parser_spec.rb
 - spec/poparser/po_spec.rb
 - spec/poparser/poparser_spec.rb
 - spec/poparser/tokenizer_spec.rb
-- spec/poparser/transformer_spec.rb
 - spec/spec_helper.rb
+- spec/utils/random_pofile_generator.rb

data/lib/poparser/parser.rb

@@ -1,67 +0,0 @@
-module PoParser
-  class Parser < Parslet::Parser
-    root(:document)
-
-    rule(:document) { lines.repeat }
-    rule(:lines)    { comments | entries }
-
-    # Comments
-    rule(:comments) do
-      reference |
-      extracted_comment | flag |
-      previous_untraslated_string |
-      cached |
-      translator_comment
-    end
-
-    rule(:translator_comment)         { spaced('#') >> comment_text_line.as(:translator_comment) }
-    rule(:extracted_comment)          { spaced('#.') >> comment_text_line.as(:extracted_comment) }
-    rule(:reference)                   { spaced('#:') >> comment_text_line.as(:reference) }
-    rule(:flag)                       { spaced('#,') >> comment_text_line.as(:flag) }
-    rule(:previous_untraslated_string){ spaced('#|') >> comment_text_line.as(:previous_untraslated_string) }
-    rule(:cached)                     { spaced('#~') >> comment_text_line.as(:cached) }
-
-    # Entries
-    rule(:entries) do
-      msgid.as(:msgid) |
-      msgid_plural.as(:msgid_plural) |
-      msgstr.as(:msgstr) |
-      msgstr_plural.as(:msgstr_plural) |
-      msgctxt.as(:msgctxt)
-    end
-
-    rule(:multiline)    { str('"').present? >> msg_text_line.repeat.maybe }
-    rule(:msgid)        { spaced('msgid') >> msg_text_line >> multiline.repeat }
-    rule(:msgid_plural) { spaced('msgid_plural') >> msg_text_line >> multiline.repeat }
-
-    rule(:msgstr)       { spaced('msgstr') >> msg_text_line >> multiline.repeat }
-    rule(:msgstr_plural){ str('msgstr') >> bracketed(match["[0-9]"].as(:plural_id)) >> space? >> msg_text_line >> multiline.repeat }
-    rule(:msgctxt)      { spaced('msgctxt') >> msg_text_line >> multiline.repeat }
-
-    # Helpers
-    rule(:space)       { match['\p{Blank}'].repeat } #match only whitespace and not newline
-    rule(:space?)      { space.maybe }
-    rule(:newline)     { match["\n"] }
-    rule(:eol)         { newline | any.absent? }
-    rule(:character)   { escaped | text }
-    rule(:text)        { any }
-    rule(:escaped)     { str('\\') >> any }
-    rule(:msg_line_end){ str('"') >> space? >> eol }
-
-    rule(:comment_text_line) do
-      (eol.absent? >> character).repeat.maybe.as(:text) >> eol
-    end
-
-    rule(:msg_text_line) do
-      str('"') >> (msg_line_end.absent? >> character).repeat.maybe.as(:text) >> msg_line_end
-    end
-
-    def bracketed(atom)
-      str('[') >> atom >> str(']')
-    end
-
-    def spaced(character)
-      str(character) >> space?
-    end
-  end
-end

data/lib/poparser/transformer.rb

@@ -1,59 +0,0 @@
-module PoParser
-  # Converts the array returned from {Parser} to a usable hash
-  class Transformer
-    def initialize
-      @hash = {}
-      super
-    end
-
-    def transform(obj)
-      apply_transforms(obj).each do |hash|
-        merge(hash)
-      end
-      @hash
-    end
-
-  private
-    # @Note: There was a problem applying all rules together. I don't know
-    #   in what order Parslet run rules, but it's not in order. I ended up
-    #   making two separate transform and feed one output to the other.
-    def first_transform
-      Parslet::Transform.new do
-        rule(:msgstr_plural => subtree(:plural)) do
-          if plural.is_a? Array
-            { "msgstr\[#{plural[0][:plural_id]}\]".to_sym => plural }
-          else
-            { "msgstr\[#{plural[:plural_id]}\]".to_sym => plural }
-          end
-        end
-
-        rule(:text => simple(:txt)) { txt.to_s.chomp }
-      end
-    end
-
-    def second_transform
-      Parslet::Transform.new do
-        rule(:plural_id => simple(:id), :text => simple(:txt)) { txt }
-      end
-    end
-
-    def apply_transforms(hash)
-      first  = first_transform.apply(hash)
-      second_transform.apply(first)
-    end
-
-    # Merges two hashed together. If both hashes have common keys it
-    # will create an array of them
-    #
-    # @return [Hash]
-    def merge(newh)
-      @hash.merge!(newh) do |key, oldval, newval|
-        if oldval.is_a? Array
-          oldval << newval
-        else
-          Array.new [oldval, newval]
-        end
-      end
-    end
-  end
-end

data/spec/poparser/parser_spec.rb

@@ -1,72 +0,0 @@
-# encoding: utf-8
-require 'spec_helper'
-
-describe PoParser::Parser do
-  let(:po) { PoParser::Parser.new }
-
-  context(:comments) do
-    let(:tc)  { po.translator_comment }
-    let(:rc)  { po.reference }
-    let(:ec)  { po.extracted_comment }
-    let(:fc)  { po.flag }
-    let(:pusc){ po.previous_untraslated_string }
-
-    it 'parses the translator comment' do
-      expect(tc).to parse("# Persian translation for damned-lies 123123\n")
-      expect(tc).to parse("# Copyright (C) 2012 damned-lies's COPYRIGHT HOLDER\n")
-      expect(tc).to parse("# Arash Mousavi <mousavi.arash@gmail.com>, 2014.\n")
-    end
-
-    it 'parses refrence comment' do
-      expect(rc).to parse("#: database-content.py:1 database-content.py:129 settings.py:52\n")
-    end
-
-    it 'parses extracted_comment' do
-      expect(ec).to parse("#. database-content.py:1 database-content.py:129 settings.py:52\n")
-    end
-
-    it 'parses flag_comment' do
-      expect(fc).to parse("#, python-format\n")
-    end
-
-    it 'parses previous_untraslated_string' do
-      expect(pusc).to parse("#| msgid \"\"\n")
-      expect(pusc).to parse("#| \"Hello,\\n\"\n")
-      expect(pusc).to parse("#| \"The new state of %(module)s - %(branch)s - %(domain)s (%(language)s) is \"\n")
-    end
-  end
-
-  context 'Entries' do
-    let(:msgid) { po.msgid }
-    let(:msgstr){ po.msgstr }
-    let(:pofile){ Pathname.new('spec/poparser/fixtures/multiline.po').realpath }
-
-    it 'parses msgid' do
-      expect(msgid).to parse "msgid \"The new state of %(module)s - %(branch)s - %(domain)s (%(language)s) is now \"\n"
-      expect(msgid).to parse "msgid \"The new \"state\" of %(module)s - %(branch)s - %(domain)s (%(language)s) is now \"\n"
-      expect(msgid).to parse "msgid     \"The new \"state\" of %(module)s - %(branch)s - %(domain)s (%(language)s) is now \"\n"
-    end
-
-    it 'parses msgstr' do
-      expect(msgstr).to parse "msgstr \"The new state of %(module)s - %(branch)s - %(domain)s (%(language)s) is now \"\n"
-      expect(msgstr).to parse "msgstr \"فعالیت نامعتبر. شاید یک نفر دیگر دقیقا قبل از شما یک فعالیت دیگر ارسال کرده ۱۲۳۱۲۳۱safda \"\n"
-      expect(msgstr).to parse "msgstr     \"The new state of %(module)s - %(branch)s - %(domain)s (%(language)s) is now \"\n"
-    end
-
-    it 'parses multiline entries' do
-      data = pofile.read
-      result = [{:msgid=>[{:text=>""}, {:text=>"first"}, {:text=>"second"}]}, {:msgstr=>[{:text=>""}, {:text=>"aval"}, {:text=>"dovom"}]}]
-      expect(po.parse data).to eq(result)
-    end
-
-    it 'parses plural msgstr entries' do
-      str1 = "msgstr[0] \"\""
-      str2 = "msgstr[0]  \"\""
-      str3 = "msgstr[0]\"\""
-      result = [{:msgstr_plural=>{:plural_id=>"0", :text=>""}}]
-      expect(po.parse(str1)).to eq(result)
-      expect(po.parse(str2)).to eq(result)
-      expect(po.parse(str3)).to eq(result)
-    end
-  end
-end

data/spec/poparser/transformer_spec.rb

@@ -1,24 +0,0 @@
-# encoding: utf-8
-require "spec_helper"
-
-describe PoParser::Transformer do
-  let(:trans){ PoParser::Transformer.new }
-
-  it 'transforms the returned array from parslet to a usable hash' do
-    parslet_array = [{:translator_comment=>"Persian translation\n"}, {:translator_comment=>"Copyright\n"}, {:msgid=>"\"test\"\n"}]
-    transformed_hash = {:translator_comment=>["Persian translation\n", "Copyright\n"], :msgid=>"\"test\"\n"}
-    expect(trans.transform(parslet_array)).to eq(transformed_hash)
-  end
-
-  it 'transforms plural msgstr forms correctly' do
-    data = [{:msgstr_plural=>{:plural_id=>"0", :text=>"this is a txt"}}]
-    result = { :'msgstr[0]' => "this is a txt" }
-    expect(trans.transform(data)).to eq(result)
-  end
-
-  it 'transforms multiline plural msgstr forms correctly' do
-    data = [{:msgstr_plural=>[{:plural_id=>"0", :text=>"this is a txt"}, {:text => 'some text'}]}]
-    result = { :'msgstr[0]' => ["this is a txt", "some text"] }
-    expect(trans.transform(data)).to eq(result)
-  end
-end