Refactor dependencymatcher.pyx to use list comps and enumerate. (#8956)

* Refactor to use list comps and enumerate.

Replace loops that append to a list with a list comprehensions where this does not change the behavior; replace range(len(...)) loops with enumerate. Correct one typo in a comment. Replace a call to set() with a set literal.

* Undo double assignment.

Expand `tokens_to_key[j] = k = self._get_matcher_key(key, i, j)` to two statements.

Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com>

* Sign contributors agreement

Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com>

.github/contributors/swfarnsworth.md

@@ -0,0 +1,88 @@
+## 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                           |  Steele Farnsworth                    |
+| Company name (if applicable)   |                      |
+| Title or role (if applicable)  |                      |
+| Date                           |  13 August, 2021                    |
+| GitHub username                |   swfarnsworth                   |
+| Website (optional)             |                      |
+

spacy/matcher/dependencymatcher.pyx

@@ -3,7 +3,6 @@ from typing import List
 from collections import defaultdict
 from itertools import product
 
-import numpy
 import warnings
 
 from .matcher cimport Matcher
@@ -122,9 +121,7 @@ cdef class DependencyMatcher:
                     raise ValueError(Errors.E099.format(key=key))
                 visited_nodes[relation["RIGHT_ID"]] = True
             else:
-                required_keys = set(
+                required_keys = {"RIGHT_ID", "RIGHT_ATTRS", "REL_OP", "LEFT_ID"}
-                    ("RIGHT_ID", "RIGHT_ATTRS", "REL_OP", "LEFT_ID")
-                )
                 relation_keys = set(relation.keys())
                 missing = required_keys - relation_keys
                 if missing:
@@ -179,28 +176,22 @@ cdef class DependencyMatcher:
         self._callbacks[key] = on_match
 
         # Add 'RIGHT_ATTRS' to self._patterns[key]
-        _patterns = []
+        _patterns = [[[pat["RIGHT_ATTRS"]] for pat in pattern] for pattern in patterns]
-        for pattern in patterns:
-            token_patterns = []
-            for i in range(len(pattern)):
-                token_pattern = [pattern[i]["RIGHT_ATTRS"]]
-                token_patterns.append(token_pattern)
-            _patterns.append(token_patterns)
         self._patterns[key].extend(_patterns)
 
         # Add each node pattern of all the input patterns individually to the
         # matcher. This enables only a single instance of Matcher to be used.
         # Multiple adds are required to track each node pattern.
         tokens_to_key_list = []
-        for i in range(len(_patterns)):
+        for i, current_patterns in enumerate(_patterns):
 
             # Preallocate list space
-            tokens_to_key = [None]*len(_patterns[i])
+            tokens_to_key = [None] * len(current_patterns)
 
             # TODO: Better ways to hash edges in pattern?
-            for j in range(len(_patterns[i])):
+            for j, _pattern in enumerate(current_patterns):
                 k = self._get_matcher_key(key, i, j)
-                self._matcher.add(k, [_patterns[i][j]])
+                self._matcher.add(k, [_pattern])
                 tokens_to_key[j] = k
 
             tokens_to_key_list.append(tokens_to_key)
@@ -337,7 +328,7 @@ cdef class DependencyMatcher:
         # position of the matched tokens
         for candidate_match in product(*all_positions):
 
-            # A potential match is a valid match if all relationhips between the
+            # A potential match is a valid match if all relationships between the
             # matched tokens are satisfied.
             is_valid = True
             for left_idx in range(len(candidate_match)):
@@ -424,18 +415,10 @@ cdef class DependencyMatcher:
         return []
 
     def _right_sib(self, doc, node):
-        candidate_children = []
+        return [doc[child.i] for child in doc[node].head.children if child.i > node]
-        for child in list(doc[node].head.children):
-            if child.i > node:
-                candidate_children.append(doc[child.i])
-        return candidate_children
 
     def _left_sib(self, doc, node):
-        candidate_children = []
+        return [doc[child.i] for child in doc[node].head.children if child.i < node]
-        for child in list(doc[node].head.children):
-            if child.i < node:
-                candidate_children.append(doc[child.i])
-        return candidate_children
 
     def _normalize_key(self, key):
         if isinstance(key, basestring):