make idx available via to_array (#5030)

.github/contributors/MisterKeefe.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 GmbH](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:
+
+    * [ ] 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                           |      Tom Keefe       |
+| Company name (if applicable)   |          /           |
+| Title or role (if applicable)  |          /           |
+| Date                           |   18 February 2020   |
+| GitHub username                |     MisterKeefe      |
+| Website (optional)             |          /           |

spacy/attrs.pxd

@@ -92,3 +92,5 @@ cdef enum attr_id_t:
     LANG
     ENT_KB_ID = symbols.ENT_KB_ID
     ENT_ID = symbols.ENT_ID
+
+    IDX

spacy/attrs.pyx

@@ -91,6 +91,7 @@ IDS = {
     "SPACY": SPACY,
     "PROB": PROB,
     "LANG": LANG,
+    "IDX": IDX
 }
 
 

spacy/symbols.pxd

@@ -463,3 +463,5 @@ cdef enum symbol_t:
 
     ENT_KB_ID
     ENT_ID
+
+    IDX

spacy/symbols.pyx

@@ -93,6 +93,7 @@ IDS = {
     "SPACY": SPACY,
     "PROB": PROB,
     "LANG": LANG,
+    "IDX": IDX,
 
     "ADJ": ADJ,
     "ADP": ADP,

spacy/tests/doc/test_array.py

@@ -66,3 +66,14 @@ def test_doc_array_to_from_string_attrs(en_vocab, attrs):
     words = ["An", "example", "sentence"]
     doc = Doc(en_vocab, words=words)
     Doc(en_vocab, words=words).from_array(attrs, doc.to_array(attrs))
+
+
+def test_doc_array_idx(en_vocab):
+    """Test that Doc.to_array can retrieve token start indices"""
+    words = ["An", "example", "sentence"]
+    doc = Doc(en_vocab, words=words)
+    offsets = Doc(en_vocab, words=words).to_array("IDX")
+
+    assert offsets[0] == 0
+    assert offsets[1] == 3
+    assert offsets[2] == 11

spacy/tokens/doc.pyx

@@ -23,7 +23,7 @@ from ..lexeme cimport Lexeme, EMPTY_LEXEME
 from ..typedefs cimport attr_t, flags_t
 from ..attrs cimport ID, ORTH, NORM, LOWER, SHAPE, PREFIX, SUFFIX, CLUSTER
 from ..attrs cimport LENGTH, POS, LEMMA, TAG, DEP, HEAD, SPACY, ENT_IOB
-from ..attrs cimport ENT_TYPE, ENT_ID, ENT_KB_ID, SENT_START, attr_id_t
+from ..attrs cimport ENT_TYPE, ENT_ID, ENT_KB_ID, SENT_START, IDX, attr_id_t
 from ..parts_of_speech cimport CCONJ, PUNCT, NOUN, univ_pos_t
 
 from ..attrs import intify_attrs, IDS
@@ -73,6 +73,8 @@ cdef attr_t get_token_attr(const TokenC* token, attr_id_t feat_name) nogil:
         return token.ent_id
     elif feat_name == ENT_KB_ID:
         return token.ent_kb_id
+    elif feat_name == IDX:
+        return token.idx
     else:
         return Lexeme.get_struct_attr(token.lex, feat_name)