From 26aee70d95792b904c64cb30b3e2625ff750e9eb Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?S=C3=B8ren=20Lind=20Kristiansen?= Date: Fri, 12 Jul 2019 15:20:42 +0200 Subject: [PATCH 1/6] Make Danish tokenizer split on forward slash --- spacy/lang/da/punctuation.py | 3 ++- spacy/lang/da/tokenizer_exceptions.py | 8 ++++++++ spacy/tests/lang/da/test_exceptions.py | 24 ++++++++++++++++++++++++ 3 files changed, 34 insertions(+), 1 deletion(-) diff --git a/spacy/lang/da/punctuation.py b/spacy/lang/da/punctuation.py index cf18ca36b..b6b852c55 100644 --- a/spacy/lang/da/punctuation.py +++ b/spacy/lang/da/punctuation.py @@ -14,10 +14,11 @@ _infixes = ( + [ r"(?<=[{al}])\.(?=[{au}])".format(al=ALPHA_LOWER, au=ALPHA_UPPER), r"(?<=[{a}])[,!?](?=[{a}])".format(a=ALPHA), - r'(?<=[{a}])[:<>=](?=[{a}])'.format(a=ALPHA), + r"(?<=[{a}])[:<>=](?=[{a}])".format(a=ALPHA), r"(?<=[{a}]),(?=[{a}])".format(a=ALPHA), r"(?<=[{a}])([{q}\)\]\(\[])(?=[{a}])".format(a=ALPHA, q=_quotes), r"(?<=[{a}])--(?=[{a}])".format(a=ALPHA), + r"(?<=[{a}0-9])[:<>=/](?=[{a}])".format(a=ALPHA), ] ) diff --git a/spacy/lang/da/tokenizer_exceptions.py b/spacy/lang/da/tokenizer_exceptions.py index be7528b23..d669fb981 100644 --- a/spacy/lang/da/tokenizer_exceptions.py +++ b/spacy/lang/da/tokenizer_exceptions.py @@ -52,6 +52,7 @@ for exc_data in [ {ORTH: "Ons.", LEMMA: "onsdag"}, {ORTH: "Fre.", LEMMA: "fredag"}, {ORTH: "Lør.", LEMMA: "lørdag"}, + {ORTH: "og/eller", LEMMA: "og/eller", NORM: "og/eller", TAG: "CC"}, ]: _exc[exc_data[ORTH]] = [exc_data] @@ -64,6 +65,8 @@ for orth in [ "mik.", "pers.", "A.D.", + "A/B", + "a/s", "A/S", "B.C.", "BK.", @@ -79,7 +82,9 @@ for orth in [ "Kprs.", "L.A.", "Ll.", + "m/k", "m/s", + "m/sek.", "M/S", "Mag.", "Mr.", @@ -90,6 +95,7 @@ for orth in [ "Sdr.", "Skt.", "Spl.", + "TCP/IP", "Vg.", ]: _exc[orth] = [{ORTH: orth}] @@ -141,6 +147,7 @@ for orth in [ "brolægn.", "bto.", "bygn.", + "c/o", "ca.", "cand.", "d.d.", @@ -293,6 +300,7 @@ for orth in [ "kgl.", "kl.", "kld.", + "km/t", "knsp.", "komm.", "kons.", diff --git a/spacy/tests/lang/da/test_exceptions.py b/spacy/tests/lang/da/test_exceptions.py index 87ea5acd6..a522ab5e8 100644 --- a/spacy/tests/lang/da/test_exceptions.py +++ b/spacy/tests/lang/da/test_exceptions.py @@ -43,3 +43,27 @@ def test_da_tokenizer_handles_custom_base_exc(da_tokenizer): def test_da_tokenizer_norm_exceptions(da_tokenizer, text, norm): tokens = da_tokenizer(text) assert tokens[0].norm_ == norm + + +@pytest.mark.parametrize( + "text,n_tokens", + [ + ("Godt og/eller skidt", 3), + ("Kør 4 km/t på vejen", 5), + ("Det blæser 12 m/s.", 5), + ("Det blæser 12 m/sek. på havnen", 6), + ("Windows 8/Windows 10", 5), + ("Billeten virker til bus/tog/metro", 8), + ("26/02/2019", 1), + ("Kristiansen c/o Madsen", 3), + ("Sprogteknologi a/s", 2), + ("De boede i A/B Bellevue", 5), + ("Rotorhastigheden er 3400 o/m.", 5), + ("Jeg købte billet t/r.", 5), + ("Murerarbejdsmand m/k søges", 3), + ("Netværket kører over TCP/IP", 4), + ], +) +def test_da_tokenizer_slash(da_tokenizer, text, n_tokens): + tokens = da_tokenizer(text) + assert len(tokens) == n_tokens From 72810268793a3ee72259a712505909edba1711f4 Mon Sep 17 00:00:00 2001 From: Ines Montani Date: Fri, 12 Jul 2019 17:40:00 +0200 Subject: [PATCH 2/6] Increment version [ci skip] --- spacy/about.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/spacy/about.py b/spacy/about.py index 8fb7d23bc..16e5e9522 100644 --- a/spacy/about.py +++ b/spacy/about.py @@ -4,7 +4,7 @@ # fmt: off __title__ = "spacy" -__version__ = "2.1.5" +__version__ = "2.1.6" __summary__ = "Industrial-strength Natural Language Processing (NLP) with Python and Cython" __uri__ = "https://spacy.io" __author__ = "Explosion AI" From c345c042b0b2c2b8b1607f8f2a8f8ebbe745aa88 Mon Sep 17 00:00:00 2001 From: Matthew Honnibal Date: Fri, 12 Jul 2019 17:48:16 +0200 Subject: [PATCH 3/6] Fix symbol alignment --- spacy/symbols.pxd | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/spacy/symbols.pxd b/spacy/symbols.pxd index 4501861a2..5922ee588 100644 --- a/spacy/symbols.pxd +++ b/spacy/symbols.pxd @@ -81,7 +81,6 @@ cdef enum symbol_t: DEP ENT_IOB ENT_TYPE - ENT_KB_ID HEAD SENT_START SPACY @@ -461,3 +460,5 @@ cdef enum symbol_t: xcomp acl + + ENT_KB_ID From ef666656b397b6ec6c5f2693c22afd5a65dea9d3 Mon Sep 17 00:00:00 2001 From: Matthew Honnibal Date: Fri, 12 Jul 2019 17:59:47 +0200 Subject: [PATCH 4/6] Fix attrs alignment --- spacy/attrs.pxd | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/spacy/attrs.pxd b/spacy/attrs.pxd index c5ba8d765..d9aca078c 100644 --- a/spacy/attrs.pxd +++ b/spacy/attrs.pxd @@ -1,4 +1,6 @@ # Reserve 64 values for flag features +from . cimport symbols + cdef enum attr_id_t: NULL_ATTR IS_ALPHA @@ -82,10 +84,10 @@ cdef enum attr_id_t: DEP ENT_IOB ENT_TYPE - ENT_KB_ID HEAD SENT_START SPACY PROB LANG + ENT_KB_ID = symbols.ENT_KB_ID From 9a86d95ea2ec12d307a0cfac77cf3d13d142728a Mon Sep 17 00:00:00 2001 From: pmbaumgartner <5107405+pmbaumgartner@users.noreply.github.com> Date: Sun, 14 Jul 2019 20:23:54 -0400 Subject: [PATCH 5/6] fix custom attribute links --- website/docs/usage/rule-based-matching.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/website/docs/usage/rule-based-matching.md b/website/docs/usage/rule-based-matching.md index 2354092f0..46cb1dacb 100644 --- a/website/docs/usage/rule-based-matching.md +++ b/website/docs/usage/rule-based-matching.md @@ -169,7 +169,7 @@ rule-based matching are: |  `LIKE_NUM`, `LIKE_URL`, `LIKE_EMAIL` | bool | Token text resembles a number, URL, email. | |  `POS`, `TAG`, `DEP`, `LEMMA`, `SHAPE` | unicode | The token's simple and extended part-of-speech tag, dependency label, lemma, shape. | | `ENT_TYPE` | unicode | The token's entity label. | -| `_` 2.1 | dict | Properties in [custom extension attributes](/processing-pipelines#custom-components-attributes). | +| `_` 2.1 | dict | Properties in [custom extension attributes](/usage/processing-pipelines#custom-components-attributes). | @@ -1140,7 +1140,7 @@ To apply this logic automatically when we process a text, we can add it to the above logic also expects that entities are merged into single tokens. spaCy ships with a handy built-in `merge_entities` that takes care of that. Instead of just printing the result, you could also write it to -[custom attributes](/processing-pipelines#custom-components-attributes) on the +[custom attributes](/usage/processing-pipelines#custom-components-attributes) on the entity `Span` – for example `._.orgs` or `._.prev_orgs` and `._.current_orgs`. > #### Merging entities From 931e87f927f1dab0c568bd3bb8339219293ed16a Mon Sep 17 00:00:00 2001 From: pmbaumgartner <5107405+pmbaumgartner@users.noreply.github.com> Date: Sun, 14 Jul 2019 20:46:06 -0400 Subject: [PATCH 6/6] contributor agreement --- .github/contributors/pmbaumgartner.md | 106 ++++++++++++++++++++++++++ 1 file changed, 106 insertions(+) create mode 100644 .github/contributors/pmbaumgartner.md diff --git a/.github/contributors/pmbaumgartner.md b/.github/contributors/pmbaumgartner.md new file mode 100644 index 000000000..f548cb854 --- /dev/null +++ b/.github/contributors/pmbaumgartner.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 | Peter Baumgartner | +| Company name (if applicable) | | +| Title or role (if applicable) | | +| Date | July 14, 2019 | +| GitHub username | pmbaumgartner | +| Website (optional) | pmbaumgartner.github.io |