diff --git a/.github/contributors/jonesmartins.md b/.github/contributors/jonesmartins.md
new file mode 100644
index 000000000..5663f6193
--- /dev/null
+++ b/.github/contributors/jonesmartins.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:
+
+ * [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 | Jones Martins |
+| Company name (if applicable) | |
+| Title or role (if applicable) | |
+| Date | 2020-06-10 |
+| GitHub username | jonesmartins |
+| Website (optional) | |
diff --git a/.github/workflows/issue-manager.yml b/.github/workflows/issue-manager.yml
index b789494a2..3fb42ed01 100644
--- a/.github/workflows/issue-manager.yml
+++ b/.github/workflows/issue-manager.yml
@@ -20,9 +20,10 @@ jobs:
token: ${{ secrets.GITHUB_TOKEN }}
config: >
{
- "answered": {
- "delay": "P3D",
+ "resolved": {
+ "delay": "P7D",
"message": "This issue has been automatically closed because it was answered and there was no follow-up discussion.",
- "remove_label": true
+ "remove_label_on_comment": true,
+ "remove_label_on_close": true
}
}
diff --git a/spacy/lang/en/tokenizer_exceptions.py b/spacy/lang/en/tokenizer_exceptions.py
index 6a553052b..964a714ae 100644
--- a/spacy/lang/en/tokenizer_exceptions.py
+++ b/spacy/lang/en/tokenizer_exceptions.py
@@ -139,7 +139,7 @@ for pron in ["he", "she", "it"]:
# W-words, relative pronouns, prepositions etc.
-for word in ["who", "what", "when", "where", "why", "how", "there", "that"]:
+for word in ["who", "what", "when", "where", "why", "how", "there", "that", "this", "these", "those"]:
for orth in [word, word.title()]:
_exc[orth + "'s"] = [
{ORTH: orth, LEMMA: word, NORM: word},
@@ -399,6 +399,14 @@ _other_exc = {
{ORTH: "Let", LEMMA: "let", NORM: "let"},
{ORTH: "'s", LEMMA: PRON_LEMMA, NORM: "us"},
],
+ "c'mon": [
+ {ORTH: "c'm", NORM: "come", LEMMA: "come"},
+ {ORTH: "on"}
+ ],
+ "C'mon": [
+ {ORTH: "C'm", NORM: "come", LEMMA: "come"},
+ {ORTH: "on"}
+ ]
}
_exc.update(_other_exc)
diff --git a/spacy/tests/lang/en/test_exceptions.py b/spacy/tests/lang/en/test_exceptions.py
index a78e1815f..1ff64eff2 100644
--- a/spacy/tests/lang/en/test_exceptions.py
+++ b/spacy/tests/lang/en/test_exceptions.py
@@ -46,7 +46,7 @@ def test_en_tokenizer_doesnt_split_apos_exc(en_tokenizer, text):
assert tokens[0].text == text
-@pytest.mark.parametrize("text", ["we'll", "You'll", "there'll"])
+@pytest.mark.parametrize("text", ["we'll", "You'll", "there'll", "this'll", "those'll"])
def test_en_tokenizer_handles_ll_contraction(en_tokenizer, text):
tokens = en_tokenizer(text)
assert len(tokens) == 2
diff --git a/website/src/templates/models.js b/website/src/templates/models.js
index 5bba1922b..3c5e9d2a4 100644
--- a/website/src/templates/models.js
+++ b/website/src/templates/models.js
@@ -1,4 +1,4 @@
-import React, { useEffect, useState, useMemo } from 'react'
+import React, { useEffect, useState, useMemo, Fragment } from 'react'
import { StaticQuery, graphql } from 'gatsby'
import { window } from 'browser-monads'
@@ -83,15 +83,24 @@ function formatVectors(data) {
function formatAccuracy(data) {
if (!data) return null
- const labels = { tags_acc: 'TAG', ents_f: 'NER F', ents_p: 'NER P', ents_r: 'NER R' }
+ const labels = {
+ las: 'LAS',
+ uas: 'UAS',
+ tags_acc: 'TAG',
+ ents_f: 'NER F',
+ ents_p: 'NER P',
+ ents_r: 'NER R',
+ }
const isSyntax = key => ['tags_acc', 'las', 'uas'].includes(key)
const isNer = key => key.startsWith('ents_')
- return Object.keys(data).map(key => ({
- label: labels[key] || key.toUpperCase(),
- value: data[key].toFixed(2),
- help: MODEL_META[key],
- type: isNer(key) ? 'ner' : isSyntax(key) ? 'syntax' : null,
- }))
+ return Object.keys(data)
+ .filter(key => labels[key])
+ .map(key => ({
+ label: labels[key],
+ value: data[key].toFixed(2),
+ help: MODEL_META[key],
+ type: isNer(key) ? 'ner' : isSyntax(key) ? 'syntax' : null,
+ }))
}
function formatModelMeta(data) {
@@ -115,11 +124,11 @@ function formatModelMeta(data) {
function formatSources(data = []) {
const sources = data.map(s => (isString(s) ? { name: s } : s))
return sources.map(({ name, url, author }, i) => (
- <>
+
{i > 0 && }
{name && url ? {name} : name}
{author && ` (${author})`}
-
+
))
}
@@ -308,12 +317,12 @@ const Model = ({ name, langId, langName, baseUrl, repo, compatibility, hasExampl