persian 0.0.0 → 0.2.2

data/lib/persian/text/text.rb

@@ -0,0 +1,214 @@
+# -*- coding: UTF-8 -*-
+
+# Persian module
+module Persian
+  # Persian Text class
+  # Digest Persian texts
+  class Text
+    # Replace Arabic characters with Persian characters.
+    def self.character(text)
+      AR_FA_CHAR.each { |k, v| text.gsub!(k, v) }
+      text
+    end
+
+    # Remove extra spaces in text
+    def self.remove_extra_spaces(text)
+      text = text.split.join(' ')
+      text = text.split('‌').join('‌')
+      text
+    end
+
+    # Remove Arabic harecats from text
+    def self.remove_harekats(text)
+      HAREKATS.each { |v| text = text.gsub(v, '') }
+      text
+    end
+
+    # Remove All barckets
+    def self.remove_brackets(text)
+      BRACKETS.each { |v| text = text.gsub(v, '') }
+      text
+    end
+
+    # Remove Persian signs
+    def self.remove_signs(text, with = '')
+      return '' if text.nil?
+      SIGNS.each { |v| text = text.gsub(v, with) }
+      text
+    end
+
+    def self.replace_zwnj_with_space(text)
+      text = text.gsub(/(‌)/, ' ')
+      text
+    end
+
+    # Replace general brackets with one type brackets
+    # Default: 	0xAB & 	0xBB
+    def self.general_brackets(text, left = '«', right = '»')
+      text = text.gsub(/"(.*?)"/, left + '\1' + right)
+      text = text.gsub(/\[(.*?)\]/, left + '\1' + right)
+      text = text.gsub(/\{(.*?)\}/, left + '\1' + right)
+      text = text.gsub(/\((.*?)\)/, left + '\1' + right)
+      text
+    end
+
+    # Add '‌ی' after names that end with ه, ا, و
+    def self.fix_y_after_vowel(text)
+      text += '‌ی' if END_VOWEL.include? text[-1]
+      text
+    end
+
+    # Replace Space with Zero-width none-joiner after می and نمی
+    def self.replace_zwnj_mi(text)
+      mi = 'می'
+      nmi = 'نمی'
+      text.gsub!(/(^|\s)(#{mi}|#{nmi})\s(\S+)/, '\1\2‌\3')
+      text
+    end
+
+    # Resplace ست with \sاست if lastest character before \s is ا
+    def self.ast(text)
+      a = 'ا'
+      ast = 'است'
+      st = 'ست'
+
+      text.gsub!(/(#{a})\s(#{ast})/, '\1' + st)
+      text
+    end
+
+    # Remove keshide from text
+    def self.keshide(text)
+      text.gsub!(/ـ+/, '')
+      text
+    end
+
+    # Use ی instead of ئ if next char is ی
+    # Example پائیز => پاییز
+    def self.replace_e_y(text)
+      e = 'ئ'
+      y = 'ی'
+      text.gsub!(/#{e}(#{y})/, '\1\1')
+      text
+    end
+
+    def self.three_dots(text)
+      text.gsub!(/\.{3,}/, '…')
+      text
+    end
+
+    def self.suffix(text)
+      tar = 'تر'
+      ee = 'ی'
+      n = 'ن'
+      ha = 'ها'
+      ye = 'ی'
+      text.gsub!(/\s+(#{tar}(#{ee}(#{n})?)?)|(#{ha}(#{ye})?)\s+/, '‌\1')
+      text
+    end
+
+    def self.remove_extra_question_mark(text)
+      mark = '؟'
+      text.gsub!(/(#{mark}){2,}/, '\1')
+      text
+    end
+
+    def self.add_zwnj(text, point)
+      text = text.scan(/^.{#{point}}|.+/).join('‌')
+      text
+    end
+
+    def self.remove_question_exclamation(text)
+      question = '؟'
+      exclamation = '!'
+      text.gsub!(/(#{question})+(#{exclamation})+/, '\1\2')
+      text
+    end
+
+    def self.remove_stopwords(text)
+      stopwords = ['و', 'در', 'به', 'این', 'با', 'از', 'که', 'است', 'را']
+      words = text.scan(/\S+/)
+      keywords = words.select { |word| !stopwords.include?(word) }
+      keywords.join(' ')
+    end
+
+    def self.remove_space_noghtevirgool(text)
+      noghtevirgool = '؛'
+      text.gsub!(/\s+(#{noghtevirgool})/, '\1')
+      text
+    end
+
+    def self.remove_signs_after_noghtevirgool(text)
+      signs = '[\.،؛:!؟\-…]'
+      noghtevirgool = '؛'
+      text.gsub!(/(#{noghtevirgool})[#{signs}]+/, '\1')
+      text
+    end
+
+    def self.space_after_noghtevirgool(text)
+      noghtevirgool = '؛'
+      text.gsub!(/(#{noghtevirgool})(\S)/, '\1 \2')
+      text
+    end
+
+    def self.remove_noghtevirgool_para_end(text)
+      noghtevirgool = '؛'
+      text.gsub!(/#{noghtevirgool}(\n|$)/, '.\1')
+      text
+    end
+
+    def self.remove_noghtevirgool_baz_start(text)
+      noghtevirgool = '؛'
+
+      regex = /([\(\[«])[ ‌]*[#{noghtevirgool}]/
+      text.gsub!(regex, '\1')
+      text
+    end
+
+    def self.remove_space_before_virgool(text)
+      virgool = '،'
+
+      text.gsub!(/\s+(#{virgool})/, '\1')
+      text
+    end
+
+    def self.remove_signs_after_virgool(text)
+      pattern = /(،)([ ‌]+)?([،؛:!؟\-][\.،؛:!؟\-]*|\.(?!\.))/
+
+      text.gsub!(pattern, '\1\2')
+      text
+    end
+
+    def self.space_after_virgool(text)
+      virgool = '،'
+
+      text.gsub!(/(#{virgool})(\S)/, '\1 \2')
+      text
+    end
+
+    def self.rm_char(text, char)
+      text.gsub!(/(#{char})/, '')
+      text
+    end
+
+    def self.rm_virgool_in_end(text)
+      text.gsub!(/(،)([ ‌\n]+)?$/, '.\2')
+      text
+    end
+
+    def self.space_after_dot(text)
+      text.gsub!(/(\.)(\S)/, '\1 \2')
+      text
+    end
+
+    def self.squeeze(text)
+      text.squeeze
+    end
+
+    # Remove specific character from end of text
+    # EXample: remove_postfix('پسره','ه')
+    def self.remove_postfix(text, postfix)
+      text.chomp!(postfix)
+      text
+    end
+  end
+end

data/lib/persian/tokenizer.rb

@@ -0,0 +1,56 @@
+# -*- coding: UTF-8 -*-
+
+# Persian module
+module Persian
+  # Persian tokenize class
+  class Tokenizer
+    # Basic persian word tokenizer
+    # Return an array of words
+    def self.tokenize(text)
+      symbols = ['!', '﷼', ':', '؛', '؟', '،', '-', '.']
+      pair_pre = ['(', '{', '«', '<', '[']
+      pair_post = [')', '}', '»', '>', ']']
+      prepost = ["'", '"']
+
+      # Split text with space characters
+      splits = text.split(/\s/)
+
+      return [''] if splits.empty?
+
+      options = symbols + pair_pre + pair_post + prepost
+
+      pattern = /[^#{Regexp.escape(options.join)}]+/
+      tokens = []
+
+      splits.each do |split|
+        first, middle, last = split.partition(pattern)
+        tokens << first.split unless first.empty?
+        tokens << middle unless middle.empty?
+        tokens << last.split unless last.empty?
+      end
+
+      tokens.flatten
+    end
+
+    def self.tokenize_more(text, num)
+      list = tokenize(text)
+      tokens = []
+      0.upto list.size - num do |i|
+        token = ''
+        0.upto num - 1 do |j|
+          token += list[i + j] + ' '
+        end
+        tokens.push token.strip
+      end
+
+      tokens
+    end
+
+    # Split paragraphs
+    # Return an array of paragraphs
+    def self.split_paragraphs(text)
+      text = text.split("\n").reject(&:empty?)
+      text
+    end
+  end
+end

data/lib/persian/unicode.rb

@@ -0,0 +1,42 @@
+# -*- coding: UTF-8 -*-
+
+# Persian module
+module Persian
+  # Persian Unicode class
+  class Unicode
+    def self.codepoint_to_char(char)
+      return [char].pack('U') if char.is_a? Fixnum
+      [char.hex].pack('U')
+    end
+
+    # Return text between RIGHT-TO-LETF EMBEDDING(U+202B) and Pop Directional Format(U+202C)
+    def self.rle(text)
+      lre_tag = 0x202B
+      pop_tag = 0x202C
+
+      codepoint_to_char(lre_tag) + text + codepoint_to_char(pop_tag)
+    end
+
+    # Return text between LETF-TO-RIGHT EMBEDDING(U+202A) and Pop Directional Format(U+202C)
+    def self.lre(text)
+      rle_tag = 0x202A
+      pop_tag = 0x202C
+
+      codepoint_to_char(rle_tag) + text + codepoint_to_char(pop_tag)
+    end
+
+    def self.rlo(text)
+      lro_tag = 0x202E
+      pop_tag = 0x202C
+
+      codepoint_to_char(lro_tag) + text + codepoint_to_char(pop_tag)
+    end
+
+    def self.lro(text)
+      rlo_tag = 0x202D
+      pop_tag = 0x202C
+
+      codepoint_to_char(rlo_tag) + text + codepoint_to_char(pop_tag)
+    end
+  end
+end

data/lib/persian/url.rb

@@ -0,0 +1,25 @@
+# -*- coding: UTF-8 -*-
+
+# Persian module
+module Persian
+  # Persian Unicode class
+  class Url
+    def self.urlify(text)
+      # remove brackets
+      text = Text.remove_brackets(text)
+      # remove harekats
+      text = Text.remove_harekats(text)
+      # remove slash and backslash
+      text = text.gsub(%r{(\/||\\)}, '')
+      # remove signs
+      text = Text.remove_signs(text, ' ')
+      # Remove extra spaces
+      text = Text.remove_extra_spaces(text)
+      # trim spaces from start and end of text
+      text = text.strip
+      # replace space with dash
+      text = text.gsub(/\s/, '-')
+      text
+    end
+  end
+end

data/lib/persian/version.rb

@@ -1,5 +1,6 @@
 # -*- coding: UTF-8 -*-
 
+# Persian module
 module Persian
-  VERSION = '0.0.0'
+  VERSION = '0.2.2'.freeze
 end

data/lib/persian.rb

@@ -1,42 +1,19 @@
 # -*- coding: UTF-8 -*-
 
-class Persian
-    def self.number num
+# lists
+require 'persian/list/alphabet'
+require 'persian/list/number'
+require 'persian/list/character'
+require 'persian/list/homonyms'
 
-      if num.is_a? Numeric
-        num = num.to_s
-      end
-
-      nums = {
-        # english numbers
-        "0" => "۰",
-        "1" => "۱",
-        "2" => "۲",
-        "3" => "۳",
-        "4" => "۴",
-        "5" => "۵",
-        "6" => "۶",
-        "7" => "۷",
-        "8" => "۸",
-        "9" => "۹",
-
-        #arabic numbers
-        "٠" => "۰",
-        "١" => "۱",
-        "٢" => "۲",
-        "٣" => "۳",
-        "٤" => "۴",
-        "٥" => "۵",
-        "٦" => "۶",
-        "٧" => "۷",
-        "٨" => "۸",
-        "٩" => "۹",
-      }
-
-      nums.each {|k, v|
-        num.gsub!(k, v)
-      }
-
-      return num
-    end
-end
+# classes
+require 'persian/number'
+require 'persian/text/text'
+require 'persian/text/keyboard'
+require 'persian/num_text'
+require 'persian/date'
+require 'persian/tokenizer'
+require 'persian/counter'
+require 'persian/unicode'
+require 'persian/dynamic'
+require 'persian/url'

data/persian.gemspec

@@ -0,0 +1,26 @@
+# -*- encoding: utf-8 -*-
+
+lib = File.expand_path('../lib', __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+
+require 'persian/version'
+
+Gem::Specification.new do |s|
+  s.name        = 'persian'
+  s.version     = Persian::VERSION
+  s.date        = '2022-03-25'
+  s.summary     = 'Persian language for ruby.'
+  s.description = 'A set of utilities for Persian language.'
+  s.authors     = ['Dariush Abbasi']
+  s.email       = 'poshtehani@gmail.com'
+  s.files       = `git ls-files`.split("\n")
+  s.test_files  = `git ls-files -- {spec}/*`.split("\n")
+  s.executables =
+    `git ls-files -- bin/*`.split("\n").map { |f| File.basename(f) }
+  s.require_paths = ['lib']
+  s.homepage      =
+    'http://github.com/dariubs/persian.rb'
+  s.license       = 'MIT'
+
+  s.add_development_dependency 'rspec', '3.4'
+end

data/readme.md

@@ -0,0 +1,48 @@
+<p align="center">
+    <img src="https://upload.wikimedia.org/wikipedia/commons/a/a2/Farsi.svg"
+         height="130" alt="Persian ruby gem">
+</p>
+
+<a href="https://travis-ci.org/negah/persian">
+    <img src="https://travis-ci.org/negah/persian.svg?branch=master"
+            alt="Build Status">
+</a>
+
+<a href="https://rubygems.org/gems/persian">
+    <img src="https://img.shields.io/badge/gem-persian-orange.svg"
+            alt="Ruby Gems">
+</a>
+
+<a href="https://rubygems.org/gems/persian">
+    <img src="https://img.shields.io/gem/dv/persian/stable.svg?maxAge=2592000"
+            alt="Ruby Gems downloads">
+</a>
+
+<a href="https://codeclimate.com/github/negah/persian">
+    <img src="https://codeclimate.com/github/negah/persian/badges/gpa.svg"
+            alt="Code Climate">
+</a>
+
+<p align="center"><sup><strong> Ruby gem for working with Persian text. </strong></sup></p>
+
+
+
+Install
+-----
+```shell
+gem install persian
+```
+
+Usage
+-----
+```ruby
+require 'persian'
+```
+
+Components
+----------
+incomplete.
+
+License
+-------
+Released under the MIT License.

data/spec/counter_spec.rb

@@ -0,0 +1,83 @@
+# -*- coding: UTF-8 -*-
+
+require 'spec_helper'
+
+describe 'persian counter methods' do
+  it 'should return a hash of characters with their number of occurrence' do
+    before = 'من غلام قمرم غیر قمر هیچ مگو'
+    after = {
+      'م' => 6,
+      'ن' => 1,
+      ' ' => 6,
+      'غ' => 2,
+      'ل' => 1,
+      'ا' => 1,
+      'ق' => 2,
+      'ر' => 3,
+      'ی' => 2,
+      'ه' => 1,
+      'چ' => 1,
+      'گ' => 1,
+      'و' => 1
+    }
+    arg = 'غ'
+    after_with_arg = 2
+
+    expect(Persian::Counter.character(before)).to eq(after)
+    expect(Persian::Counter.character(before, arg)).to eq(after_with_arg)
+  end
+
+  it 'should return a hash of words as key and number of occurrence of word as value' do
+    before = 'پرچم دوران هخامنشی به احتمال زیاد عقابی با بال های گشوده با قرص خورشیدی در پشت سر عقاب بوده است'
+    after = {
+      'پرچم' => 1,
+      'دوران' => 1,
+      'هخامنشی' => 1,
+      'به' => 1,
+      'احتمال' => 1,
+      'زیاد' => 1,
+      'عقابی' => 1,
+      'با' => 2,
+      'بال' => 1,
+      'های' => 1,
+      'گشوده' => 1,
+      'قرص' => 1,
+      'خورشیدی' => 1,
+      'در' => 1,
+      'پشت' => 1,
+      'سر' => 1,
+      'عقاب' => 1,
+      'بوده' => 1,
+      'است' => 1
+    }
+    arg = 'با'
+    after_with_arg = 2
+
+    expect(Persian::Counter.word(before)).to eq(after)
+    expect(Persian::Counter.word(before, arg)).to eq(after_with_arg)
+  end
+
+  it 'should return number of paragraphs' do
+    text = "
+یوهانس برامس در سال ۱۸۳۳ در شهر هامبورگ آلمان در خانواده‌ای فقیر به دنیا آمد. تحصیلات ابتدایی موسیقی را نزد پدرش که نوازنده کنترباس بود فرا گرفت.
+برامس با ویولونیست‌های مشهوری چون رمنی و یواخیم آشنا شد و در طول این آشنایی بود که رمنی موسیقی محلی مجارستان را به برامس معرفی کرد و تحت تأثیر آن برامس رقص‌های مجار خود را نوشت.
+"
+    after = 2
+
+    expect(Persian::Counter.paragraph(text)).to eq(after)
+  end
+
+  it 'shoud count uniq characters' do
+    text = 'دوستت دارم'
+    size = 8
+
+    expect(Persian::Counter.uniq_character(text)).to eq(size)
+  end
+
+  it 'shoud return length of text' do
+    text = 'راهی بزن که آهی بر ساز آن توان زد'
+    size = 33
+
+    expect(Persian::Counter.character_counter(text)).to eq(size)
+  end
+end

data/spec/dynamic_spec.rb

@@ -0,0 +1,6 @@
+# -*- coding: UTF-8 -*-
+
+require 'spec_helper'
+
+describe 'persian dynamic methods methods' do
+end

data/spec/num_text_spec.rb

@@ -0,0 +1,17 @@
+# -*- coding: UTF-8 -*-
+
+require 'spec_helper'
+
+describe 'persian number to character methods' do
+  it 'should convert english numbers to spelled persian character' do
+    before = 1234
+    after = 'یک هزار و دویست و سی و چهار'
+    expect(Persian::NumText.num_to_char(before)).to eq(after)
+  end
+
+  it 'should convert Persian numbers to spelled persian number' do
+    before = '۲۰۴۸۲۰۴۸'
+    after = 'بیست میلیون و چهارصد و هشتاد و دو هزار و چهل و هشت'
+    expect(Persian::NumText.num_to_char(before)).to eq(after)
+  end
+end