update bengali token rules for hyphen and digits (#2731)

.github/contributors/aniruddha-adhikary.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                           | Aniruddha Adhikary   |
+| Company name (if applicable)   |                      |
+| Title or role (if applicable)  |                      |
+| Date                           | 2018-09-05           |
+| GitHub username                | aniruddha-adhikary   |
+| Website (optional)             | https://adhikary.net |

spacy/lang/bn/punctuation.py

@@ -20,12 +20,11 @@ _suffixes = (_list_punct + LIST_ELLIPSES + LIST_QUOTES + LIST_ICONS +
               r'(?<=[{}(?:{})])\.'.format('|'.join([ALPHA_LOWER, r'%²\-\)\]\+', QUOTES]), _currency)])
 
 _infixes = (LIST_ELLIPSES + LIST_ICONS +
-            [r'(?<=[{}])\.(?=[{}])'.format(ALPHA_LOWER, ALPHA_UPPER),
+            [r'(?<=[0-9{zero}-{nine}])[+\-\*^=](?=[0-9{zero}-{nine}-])'.format(zero=u'০', nine=u'৯'),
              r'(?<=[{a}]),(?=[{a}])'.format(a=ALPHA),
-             r'(?<=[{a}"])[:<>=](?=[{a}])'.format(a=ALPHA),
+             r'(?<=[{a}])[{h}](?={ae})'.format(a=ALPHA, h=HYPHENS, ae=u'এ'),
-             r'(?<=[{a}])--(?=[{a}])'.format(a=ALPHA),
+             r'(?<=[{a}])[?";:=,.]*(?:{h})(?=[{a}])'.format(a=ALPHA, h=HYPHENS),
-             r'(?<=[{a}]),(?=[{a}])'.format(a=ALPHA),
+             r'(?<=[{a}"])[:<>=/](?=[{a}])'.format(a=ALPHA)])
-             r'(?<=[{a}])([{q}\)\]\(\[])(?=[\-{a}])'.format(a=ALPHA, q=_quotes)])
 
 
 TOKENIZER_PREFIXES = _prefixes

spacy/tests/lang/bn/test_tokenizer.py

@@ -10,6 +10,11 @@ PUNCTUATION_TESTS = [
     (u'আমি বাংলায় কথা কই।', [u'আমি', u'বাংলায়', u'কথা', u'কই', u'।']),
     (u'বসুন্ধরা জনসম্মুখে দোষ স্বীকার করলো না?', [u'বসুন্ধরা', u'জনসম্মুখে', u'দোষ', u'স্বীকার', u'করলো', u'না', u'?']),
     (u'টাকা থাকলে কি না হয়!', [u'টাকা', u'থাকলে', u'কি', u'না', u'হয়', u'!']),
+    (u'সরকারি বিশ্ববিদ্যালয়-এর ছাত্র নই বলেই কি এমন আচরণ?',
+     [u'সরকারি', u'বিশ্ববিদ্যালয়', u'-', u'এর', u'ছাত্র', u'নই', u'বলেই', u'কি', u'এমন', u'আচরণ', u'?']),
+    (u'তারা বলে, "ওরা খামারের মুরগি।"', [u'তারা', u'বলে', ',', '"', u'ওরা', u'খামারের', u'মুরগি', u'।', '"']),
+    (u'৩*৩=৬?', [u'৩', u'*', u'৩', '=', u'৬', '?']),
+    (u'কাঁঠাল-এর গন্ধই অন্যরকম', [u'কাঁঠাল', '-', u'এর', u'গন্ধই', u'অন্যরকম']),
 ]
 
 ABBREVIATIONS = [