Add Arabic language (#2314)

* added support for Arabic lang

* added Arabic language support

* updated conftest

.github/contributors/tzano.md

@@ -0,0 +1,106 @@
+# spaCy contributor agreement
+
+This spaCy Contributor Agreement (**"SCA"**) is based on the
+[Oracle Contributor Agreement](http://www.oracle.com/technetwork/oca-405177.pdf).
+The SCA applies to any contribution that you make to any product or project
+managed by us (the **"project"**), and sets out the intellectual property rights
+you grant to us in the contributed materials. The term **"us"** shall mean
+[ExplosionAI UG (haftungsbeschränkt)](https://explosion.ai/legal). The term
+**"you"** shall mean the person or entity identified below.
+
+If you agree to be bound by these terms, fill in the information requested
+below and include the filled-in version with your first pull request, under the
+folder [`.github/contributors/`](/.github/contributors/). The name of the file
+should be your GitHub username, with the extension `.md`. For example, the user
+example_user would create the file `.github/contributors/example_user.md`.
+
+Read this agreement carefully before signing. These terms and conditions
+constitute a binding legal agreement.
+
+## Contributor Agreement
+
+1. The term "contribution" or "contributed materials" means any source code,
+object code, patch, tool, sample, graphic, specification, manual,
+documentation, or any other material posted or submitted by you to the project.
+
+2. With respect to any worldwide copyrights, or copyright applications and
+registrations, in your contribution:
+
+    * you hereby assign to us joint ownership, and to the extent that such
+    assignment is or becomes invalid, ineffective or unenforceable, you hereby
+    grant to us a perpetual, irrevocable, non-exclusive, worldwide, no-charge,
+    royalty-free, unrestricted license to exercise all rights under those
+    copyrights. This includes, at our option, the right to sublicense these same
+    rights to third parties through multiple levels of sublicensees or other
+    licensing arrangements;
+
+    * you agree that each of us can do all things in relation to your
+    contribution as if each of us were the sole owners, and if one of us makes
+    a derivative work of your contribution, the one who makes the derivative
+    work (or has it made will be the sole owner of that derivative work;
+
+    * you agree that you will not assert any moral rights in your contribution
+    against us, our licensees or transferees;
+
+    * you agree that we may register a copyright in your contribution and
+    exercise all ownership rights associated with it; and
+
+    * you agree that neither of us has any duty to consult with, obtain the
+    consent of, pay or render an accounting to the other for any use or
+    distribution of your contribution.
+
+3. With respect to any patents you own, or that you can license without payment
+to any third party, you hereby grant to us a perpetual, irrevocable,
+non-exclusive, worldwide, no-charge, royalty-free license to:
+
+    * make, have made, use, sell, offer to sell, import, and otherwise transfer
+    your contribution in whole or in part, alone or in combination with or
+    included in any product, work or materials arising out of the project to
+    which your contribution was submitted, and
+
+    * at our option, to sublicense these same rights to third parties through
+    multiple levels of sublicensees or other licensing arrangements.
+
+4. Except as set out above, you keep all right, title, and interest in your
+contribution. The rights that you grant to us under these terms are effective
+on the date you first submitted a contribution to us, even if your submission
+took place before the date you sign these terms.
+
+5. You covenant, represent, warrant and agree that:
+
+    * Each contribution that you submit is and shall be an original work of
+    authorship and you can legally grant the rights set out in this SCA;
+
+    * to the best of your knowledge, each contribution will not violate any
+    third party's copyrights, trademarks, patents, or other intellectual
+    property rights; and
+
+    * each contribution shall be in compliance with U.S. export control laws and
+    other applicable export and import laws. You agree to notify us if you
+    become aware of any circumstance which would make any of the foregoing
+    representations inaccurate in any respect. We may publicly disclose your 
+    participation in the project, including the fact that you have signed the SCA.
+
+6. This SCA is governed by the laws of the State of California and applicable
+U.S. Federal law. Any choice of law rules will not apply.
+
+7. Please place an “x” on one of the applicable statement below. Please do NOT
+mark both statements:
+
+    * [x] I am signing on behalf of myself as an individual and no other person
+    or entity, including my employer, has or will have rights with respect to my
+    contributions.
+
+    * [ ] I am signing on behalf of my employer or a legal entity and I have the
+    actual authority to contractually bind that entity.
+
+## Contributor Details
+
+| Field                          | Entry                |
+|------------------------------- | -------------------- |
+| Name                           | Tahar Zanouda        |
+| Company name (if applicable)   |                      |
+| Title or role (if applicable)  |                      |
+| Date                           | 09-05-2018           |
+| GitHub username                | tzano                |
+| Website (optional)             |                      |

spacy/lang/ar/__init__.py

@@ -0,0 +1,31 @@
+# coding: utf8
+from __future__ import unicode_literals
+
+from .stop_words import STOP_WORDS
+from .lex_attrs import LEX_ATTRS
+from .punctuation import TOKENIZER_SUFFIXES
+
+from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
+from ..tokenizer_exceptions import BASE_EXCEPTIONS
+from ..norm_exceptions import BASE_NORMS
+from ...language import Language
+from ...attrs import LANG, NORM
+from ...util import update_exc, add_lookups
+
+
+class ArabicDefaults(Language.Defaults):
+    lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
+    lex_attr_getters.update(LEX_ATTRS)
+    lex_attr_getters[LANG] = lambda text: 'ar'
+    lex_attr_getters[NORM] = add_lookups(Language.Defaults.lex_attr_getters[NORM], BASE_NORMS)
+    tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS)
+    stop_words = STOP_WORDS
+    suffixes = TOKENIZER_SUFFIXES
+
+
+class Arabic(Language):
+    lang = 'ar'
+    Defaults = ArabicDefaults
+
+
+__all__ = ['Arabic']

spacy/lang/ar/examples.py

@@ -0,0 +1,20 @@
+# coding: utf8
+from __future__ import unicode_literals
+
+"""
+Example sentences to test spaCy and its language models.
+
+>>> from spacy.lang.ar.examples import sentences
+>>> docs = nlp.pipe(sentences)
+"""
+
+sentences = [
+    "نال الكاتب خالد توفيق  جائزة الرواية العربية في معرض الشارقة الدولي للكتاب",
+    "أين تقع دمشق ؟"
+    "كيف حالك ؟",
+    "هل يمكن ان نلتقي على الساعة الثانية عشرة ظهرا ؟",
+    "ماهي أبرز التطورات السياسية، الأمنية والاجتماعية في العالم ؟",
+    "هل بالإمكان أن نلتقي غدا؟",
+    "هناك نحو 382 مليون شخص مصاب بداء السكَّري في العالم",
+    "كشفت دراسة حديثة أن الخيل تقرأ تعبيرات الوجه وتستطيع أن تتذكر مشاعر الناس وعواطفهم"
+]

spacy/lang/ar/lex_attrs.py

@@ -0,0 +1,95 @@
+# coding: utf8
+from __future__ import unicode_literals
+from ...attrs import LIKE_NUM
+
+_num_words = set("""
+صفر
+واحد
+إثنان
+اثنان
+ثلاثة
+ثلاثه
+أربعة
+أربعه
+خمسة
+خمسه
+ستة
+سته
+سبعة
+سبعه
+ثمانية
+ثمانيه
+تسعة
+تسعه
+ﻋﺸﺮﺓ
+ﻋﺸﺮه
+عشرون
+عشرين
+ثلاثون
+ثلاثين
+اربعون
+اربعين
+أربعون
+أربعين
+خمسون
+خمسين
+ستون
+ستين
+سبعون
+سبعين
+ثمانون
+ثمانين
+تسعون
+تسعين
+مائتين
+مائتان
+ثلاثمائة
+خمسمائة
+سبعمائة
+الف
+آلاف
+ملايين
+مليون
+مليار
+مليارات
+""".split())
+
+_ordinal_words = set("""
+اول
+أول
+حاد
+واحد
+ثان
+ثاني
+ثالث
+رابع
+خامس
+سادس
+سابع
+ثامن
+تاسع
+عاشر
+""".split())
+
+
+def like_num(text):
+    """
+    check if text resembles a number
+    """
+    text = text.replace(',', '').replace('.', '')
+    if text.isdigit():
+        return True
+    if text.count('/') == 1:
+        num, denom = text.split('/')
+        if num.isdigit() and denom.isdigit():
+            return True
+    if text in _num_words:
+        return True
+    if text in _ordinal_words:
+        return True
+    return False
+
+
+LEX_ATTRS = {
+    LIKE_NUM: like_num
+}

spacy/lang/ar/punctuation.py

@@ -0,0 +1,15 @@
+# coding: utf8
+from __future__ import unicode_literals
+
+from ..punctuation import TOKENIZER_INFIXES
+from ..char_classes import LIST_PUNCT, LIST_ELLIPSES, LIST_QUOTES, CURRENCY
+from ..char_classes import QUOTES, UNITS, ALPHA, ALPHA_LOWER, ALPHA_UPPER
+
+_suffixes = (LIST_PUNCT + LIST_ELLIPSES + LIST_QUOTES +
+             [r'(?<=[0-9])\+',
+              # Arabic is written from Right-To-Left
+              r'(?<=[0-9])(?:{})'.format(CURRENCY),
+              r'(?<=[0-9])(?:{})'.format(UNITS),
+              r'(?<=[{au}][{au}])\.'.format(au=ALPHA_UPPER)])
+
+TOKENIZER_SUFFIXES = _suffixes

spacy/lang/ar/stop_words.py

@@ -0,0 +1,229 @@
+# coding: utf8
+from __future__ import unicode_literals
+
+STOP_WORDS = set("""
+من
+نحو
+لعل
+بما
+بين
+وبين
+ايضا
+وبينما
+تحت
+مثلا
+لدي
+عنه
+مع
+هي
+وهذا
+واذا
+هذان
+انه
+بينما
+أمسى
+وسوف
+ولم
+لذلك
+إلى
+منه
+منها
+كما
+ظل
+هنا
+به
+كذلك
+اما
+هما
+بعد
+بينهم
+التي
+أبو
+اذا
+بدلا
+لها
+أمام
+يلي
+حين
+ضد
+الذي
+قد
+صار
+إذا
+مابرح
+قبل
+كل
+وليست
+الذين
+لهذا
+وثي
+انهم
+باللتي
+مافتئ
+ولا
+بهذه
+بحيث
+كيف
+وله
+علي
+بات
+لاسيما
+حتى
+وقد
+و
+أما
+فيها
+بهذا
+لذا
+حيث
+لقد
+إن
+فإن
+اول
+ليت
+فاللتي
+ولقد
+لسوف
+هذه
+ولماذا
+معه
+الحالي
+بإن
+حول
+في
+عليه
+مايزال
+ولعل
+أنه
+أضحى
+اي
+ستكون
+لن
+أن
+ضمن
+وعلى
+امسى
+الي
+ذات
+ولايزال
+ذلك
+فقد
+هم
+أي
+عند
+ابن
+أو
+فهو
+فانه
+سوف
+ما
+آل
+كلا
+عنها
+وكذلك
+ليست
+لم
+وأن
+ماذا
+لو
+وهل
+اللتي
+ولذا
+يمكن
+فيه
+الا
+عليها
+وبينهم
+يوم
+وبما
+لما
+فكان
+اضحى
+اصبح
+لهم
+بها
+او
+الذى
+الى
+إلي
+قال
+والتي
+لازال
+أصبح
+ولهذا
+مثل
+وكانت
+لكنه
+بذلك
+هذا
+لماذا
+قالت
+فقط
+لكن
+مما
+وكل
+وان
+وأبو
+ومن
+كان
+مازال
+هل
+بينهن
+هو
+وما
+على
+وهو
+لأن
+واللتي
+والذي
+دون
+عن
+وايضا
+هناك
+بلا
+جدا
+ثم
+منذ
+اللذين
+لايزال
+بعض
+مساء
+تكون
+فلا
+بيننا
+لا
+ولكن
+إذ
+وأثناء
+ليس
+ومع
+فيهم
+ولسوف
+بل
+تلك
+أحد
+وهي
+وكان
+ومنها
+وفي
+ماانفك
+اليوم
+وماذا
+هؤلاء
+وليس
+له
+أثناء
+بد
+اليه
+كأن
+اليها
+بتلك
+يكون
+ولما
+هن
+والى
+كانت
+وقبل
+ان
+لدى
+""".split())

spacy/lang/ar/tokenizer_exceptions.py

@@ -0,0 +1,47 @@
+# coding: utf8
+from __future__ import unicode_literals
+
+from ...symbols import ORTH, LEMMA, TAG, NORM, PRON_LEMMA
+import re
+
+_exc = {}
+
+# time
+for exc_data in [
+    {LEMMA: "قبل الميلاد", ORTH: "ق.م"},
+    {LEMMA: "بعد الميلاد", ORTH: "ب. م"},
+    {LEMMA: "ميلادي", ORTH: ".م"},
+    {LEMMA: "هجري", ORTH: ".هـ"},
+    {LEMMA: "توفي", ORTH: ".ت"}]:
+    _exc[exc_data[ORTH]] = [exc_data]
+
+# scientific abv.
+for exc_data in [
+    {LEMMA: "صلى الله عليه وسلم", ORTH: "صلعم"},
+    {LEMMA: "الشارح", ORTH: "الشـ"},
+    {LEMMA: "الظاهر", ORTH: "الظـ"},
+    {LEMMA: "أيضًا", ORTH: "أيضـ"},
+    {LEMMA: "إلى آخره", ORTH: "إلخ"},
+    {LEMMA: "انتهى", ORTH: "اهـ"},
+    {LEMMA: "حدّثنا", ORTH: "ثنا"},
+    {LEMMA: "حدثني", ORTH: "ثنى"},
+    {LEMMA: "أنبأنا", ORTH: "أنا"},
+    {LEMMA: "أخبرنا", ORTH: "نا"},
+    {LEMMA: "مصدر سابق", ORTH: "م. س"},
+    {LEMMA: "مصدر نفسه", ORTH: "م. ن"}]:
+    _exc[exc_data[ORTH]] = [exc_data]
+
+# other abv.
+for exc_data in [
+    {LEMMA: "دكتور", ORTH: "د."},
+    {LEMMA: "أستاذ دكتور", ORTH: "أ.د"},
+    {LEMMA: "أستاذ", ORTH: "أ."},
+    {LEMMA: "بروفيسور", ORTH: "ب."}]:
+    _exc[exc_data[ORTH]] = [exc_data]
+
+for exc_data in [
+    {LEMMA: "تلفون", ORTH: "ت."},
+    {LEMMA: "صندوق بريد", ORTH: "ص.ب"}]:
+    _exc[exc_data[ORTH]] = [exc_data]
+
+TOKENIZER_EXCEPTIONS = _exc

spacy/lang/char_classes.py

@@ -3,13 +3,11 @@ from __future__ import unicode_literals
 
 import regex as re
 
-
 re.DEFAULT_VERSION = re.VERSION1
 merge_char_classes = lambda classes: '[{}]'.format('||'.join(classes))
 split_chars = lambda char: list(char.strip().split(' '))
 merge_chars = lambda char: char.strip().replace(' ', '|')
 
-
 _bengali = r'[\p{L}&&\p{Bengali}]'
 _hebrew = r'[\p{L}&&\p{Hebrew}]'
 _latin_lower = r'[\p{Ll}&&\p{Latin}]'
@@ -27,11 +25,11 @@ ALPHA = merge_char_classes(_upper + _lower + _uncased)
 ALPHA_LOWER = merge_char_classes(_lower + _uncased)
 ALPHA_UPPER = merge_char_classes(_upper + _uncased)
 
-
 _units = ('km km² km³ m m² m³ dm dm² dm³ cm cm² cm³ mm mm² mm³ ha µm nm yd in ft '
           'kg g mg µg t lb oz m/s km/h kmh mph hPa Pa mbar mb MB kb KB gb GB tb '
           'TB T G M K % км км² км³ м м² м³ дм дм² дм³ см см² см³ мм мм² мм³ нм '
-          'кг г мг м/с км/ч кПа Па мбар Кб КБ кб Мб МБ мб Гб ГБ гб Тб ТБ тб')
+          'кг г мг м/с км/ч кПа Па мбар Кб КБ кб Мб МБ мб Гб ГБ гб Тб ТБ тб'
+          'كم كم² كم³ م م² م³ سم سم² سم³ مم مم² مم³ كم غرام جرام جم كغ ملغ كوب اكواب')
 _currency = r'\$ £ € ¥ ฿ US\$ C\$ A\$ ₽ ﷼'
 
 # These expressions contain various unicode variations, including characters
@@ -45,7 +43,6 @@ _hyphens = '- – — -- --- —— ~'
 # Details: https://www.compart.com/en/unicode/category/So
 _other_symbols = r'[\p{So}]'
 
-
 UNITS = merge_chars(_units)
 CURRENCY = merge_chars(_currency)
 QUOTES = merge_chars(_quotes)

spacy/tests/conftest.py

@@ -15,7 +15,9 @@ from .. import util
 # here if it's using spaCy's tokenizer (not a different library)
 # TODO: re-implement generic tokenizer tests
 _languages = ['bn', 'da', 'de', 'en', 'es', 'fi', 'fr', 'ga', 'he', 'hu', 'id',
+              'it', 'nb', 'nl', 'pl', 'pt', 'ru', 'sv', 'tr', 'ar', 'xx']
               'it', 'nb', 'nl', 'pl', 'pt', 'ro', 'ru', 'sv', 'tr', 'xx']
+
 _models = {'en': ['en_core_web_sm'],
            'de': ['de_core_news_md'],
            'fr': ['fr_core_news_sm'],
@@ -152,6 +154,9 @@ def th_tokenizer():
 def tr_tokenizer():
     return util.get_lang_class('tr').Defaults.create_tokenizer()
 
+@pytest.fixture
+def ar_tokenizer():
+    return util.get_lang_class('ar').Defaults.create_tokenizer()
 
 @pytest.fixture
 def ru_tokenizer():

spacy/tests/lang/ar/test_exceptions.py

@@ -0,0 +1,26 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import pytest
+
+
+@pytest.mark.parametrize('text',
+                         ["ق.م", "إلخ", "ص.ب", "ت."])
+def test_ar_tokenizer_handles_abbr(ar_tokenizer, text):
+    tokens = ar_tokenizer(text)
+    assert len(tokens) == 1
+
+
+def test_ar_tokenizer_handles_exc_in_text(ar_tokenizer):
+    text = u"تعود الكتابة الهيروغليفية إلى سنة 3200 ق.م"
+    tokens = ar_tokenizer(text)
+    assert len(tokens) == 7
+    assert tokens[6].text == "ق.م"
+    assert tokens[6].lemma_ == "قبل الميلاد"
+
+
+def test_ar_tokenizer_handles_exc_in_text(ar_tokenizer):
+    text = u"يبلغ طول مضيق طارق 14كم "
+    tokens = ar_tokenizer(text)
+    print([(tokens[i].text, tokens[i].suffix_) for i in range(len(tokens))])
+    assert len(tokens) == 6

spacy/tests/lang/ar/test_text.py

@@ -0,0 +1,13 @@
+# coding: utf8
+from __future__ import unicode_literals
+
+
+def test_tokenizer_handles_long_text(ar_tokenizer):
+    text = """نجيب محفوظ مؤلف و كاتب روائي عربي، يعد من أهم الأدباء العرب خلال القرن العشرين.
+     ولد نجيب محفوظ في مدينة القاهرة، حيث ترعرع و تلقى تعليمه الجامعي في جامعتها،
+      فتمكن من نيل شهادة في الفلسفة. ألف محفوظ على مدار حياته الكثير من الأعمال الأدبية، و في مقدمتها ثلاثيته الشهيرة.
+      و قد نجح في الحصول على جائزة نوبل للآداب، ليكون بذلك العربي الوحيد الذي فاز بها."""
+
+    tokens = ar_tokenizer(text)
+    assert tokens[3].is_stop == True
+    assert len(tokens) == 77