Merge pull request #1637 from sorenlind/da_tokenization

Improve Danish tokenization

.github/contributors/sorenlind.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                           | Søren Lind Kristiansen             |
+| Company name (if applicable)   |                                    |
+| Title or role (if applicable)  |                                    |
+| Date                           | 24 November 2017                   |
+| GitHub username                | sorenlind                          |
+| Website (optional)             |                                    |

spacy/lang/da/tokenizer_exceptions.py

@@ -1,32 +1,134 @@
 # encoding: utf8
+"""
+Tokenizer Exceptions.
+Source: https://forkortelse.dk/ and various others.
+"""
+
 from __future__ import unicode_literals
 
-from ...symbols import ORTH, LEMMA, NORM
+from ...symbols import ORTH, LEMMA, NORM, TAG, PUNCT
 
 
 _exc = {}
 
+# Abbreviations for weekdays "søn." (for "søndag") as well as "Tor." and "Tors."
+# (for "torsdag") are left out because they are ambiguous. The same is the case
+# for abbreviations "jul." and "Jul." ("juli").
 for exc_data in [
-    {ORTH: "Kbh.", LEMMA: "København", NORM: "København"},
+        {ORTH: "Kbh.", LEMMA: "København", NORM: "København"},
-    {ORTH: "Jan.", LEMMA: "januar", NORM: "januar"},
+        {ORTH: "jan.", LEMMA: "januar"},
-    {ORTH: "Feb.", LEMMA: "februar", NORM: "februar"},
+        {ORTH: "febr.", LEMMA: "februar"},
-    {ORTH: "Mar.", LEMMA: "marts", NORM: "marts"},
+        {ORTH: "feb.", LEMMA: "februar"},
-    {ORTH: "Apr.", LEMMA: "april", NORM: "april"},
+        {ORTH: "mar.", LEMMA: "marts"},
-    {ORTH: "Maj.", LEMMA: "maj", NORM: "maj"},
+        {ORTH: "apr.", LEMMA: "april"},
-    {ORTH: "Jun.", LEMMA: "juni", NORM: "juni"},
+        {ORTH: "jun.", LEMMA: "juni"},
-    {ORTH: "Jul.", LEMMA: "juli", NORM: "juli"},
+        {ORTH: "aug.", LEMMA: "august"},
-    {ORTH: "Aug.", LEMMA: "august", NORM: "august"},
+        {ORTH: "sept.", LEMMA: "september"},
-    {ORTH: "Sep.", LEMMA: "september", NORM: "september"},
+        {ORTH: "sep.", LEMMA: "september"},
-    {ORTH: "Okt.", LEMMA: "oktober", NORM: "oktober"},
+        {ORTH: "okt.", LEMMA: "oktober"},
-    {ORTH: "Nov.", LEMMA: "november", NORM: "november"},
+        {ORTH: "nov.", LEMMA: "november"},
-    {ORTH: "Dec.", LEMMA: "december", NORM: "december"}]:
+        {ORTH: "dec.", LEMMA: "december"},
+        {ORTH: "man.", LEMMA: "mandag"},
+        {ORTH: "tirs.", LEMMA: "tirsdag"},
+        {ORTH: "ons.", LEMMA: "onsdag"},
+        {ORTH: "tor.", LEMMA: "torsdag"},
+        {ORTH: "tors.", LEMMA: "torsdag"},
+        {ORTH: "fre.", LEMMA: "fredag"},
+        {ORTH: "lør.", LEMMA: "lørdag"},
+        {ORTH: "Jan.", LEMMA: "januar"},
+        {ORTH: "Febr.", LEMMA: "februar"},
+        {ORTH: "Feb.", LEMMA: "februar"},
+        {ORTH: "Mar.", LEMMA: "marts"},
+        {ORTH: "Apr.", LEMMA: "april"},
+        {ORTH: "Jun.", LEMMA: "juni"},
+        {ORTH: "Aug.", LEMMA: "august"},
+        {ORTH: "Sept.", LEMMA: "september"},
+        {ORTH: "Sep.", LEMMA: "september"},
+        {ORTH: "Okt.", LEMMA: "oktober"},
+        {ORTH: "Nov.", LEMMA: "november"},
+        {ORTH: "Dec.", LEMMA: "december"},
+        {ORTH: "Man.", LEMMA: "mandag"},
+        {ORTH: "Tirs.", LEMMA: "tirsdag"},
+        {ORTH: "Ons.", LEMMA: "onsdag"},
+        {ORTH: "Fre.", LEMMA: "fredag"},
+        {ORTH: "Lør.", LEMMA: "lørdag"}]:
     _exc[exc_data[ORTH]] = [exc_data]
 
 for orth in [
-    "A/S", "beg.", "bl.a.", "ca.", "d.s.s.", "dvs.", "f.eks.", "fr.", "hhv.",
+        "A.D.", "A/S", "aarh.", "ac.", "adj.", "adr.", "adsk.", "adv.", "afb.",
-    "if.", "iflg.", "m.a.o.", "mht.", "min.", "osv.", "pga.", "resp.", "self.",
+        "afd.", "afg.", "afk.", "afs.", "aht.", "alg.", "alk.", "alm.", "amer.",
-    "t.o.m.", "vha.", ""]:
+        "ang.", "ank.", "anl.", "anv.", "arb.", "arr.", "att.", "B.C.", "bd.",
+        "bdt.", "beg.", "begr.", "beh.", "bet.", "bev.", "bhk.", "bib.",
+        "bibl.", "bidr.", "bildl.", "bill.", "bio.", "biol.", "bk.", "BK.",
+        "bl.", "bl.a.", "borgm.", "bot.", "Boul.", "br.", "brolægn.", "bto.",
+        "bygn.", "ca.", "cand.", "Chr.", "d.", "d.d.", "d.m.", "d.s.", "d.s.s.",
+        "d.y.", "d.å.", "d.æ.", "da.", "dagl.", "dat.", "dav.", "def.", "dek.",
+        "dep.", "desl.", "diam.", "dir.", "disp.", "distr.", "div.", "dkr.",
+        "dl.", "do.", "dobb.", "Dr.", "dr.h.c", "Dronn.", "ds.", "dvs.", "e.b.",
+        "e.l.", "e.o.", "e.v.t.", "eftf.", "eftm.", "eg.", "egl.", "eks.",
+        "eksam.", "ekskl.", "eksp.", "ekspl.", "el.", "el.lign.", "emer.",
+        "endv.", "eng.", "enk.", "etc.", "etym.", "eur.", "evt.", "exam.", "f.",
+        "f.eks.", "f.m.", "f.n.", "f.o.", "f.o.m.", "f.s.v.", "f.t.", "f.v.t.",
+        "f.å.", "fa.", "fakt.", "fam.", "fem.", "ff.", "fg.", "fhv.", "fig.",
+        "filol.", "filos.", "fl.", "flg.", "fm.", "fmd.", "fol.", "forb.",
+        "foreg.", "foren.", "forf.", "fork.", "form.", "forr.", "fors.",
+        "forsk.", "forts.", "fr.", "fr.u.", "frk.", "fsva.", "fuldm.", "fung.",
+        "fx.", "fys.", "fær.", "g.d.", "g.m.", "gd.", "gdr.", "genuds.", "gl.",
+        "gn.", "gns.", "gr.", "grdl.", "gross.", "h.a.", "h.c.", "H.K.H.",
+        "H.M.", "hdl.", "henv.", "Hf.", "hhv.", "hj.hj.", "hj.spl.", "hort.",
+        "hosp.", "hpl.", "Hr.", "hr.", "hrs.", "hum.", "hvp.", "i/s", "I/S",
+        "i.e.", "ib.", "id.", "if.", "iflg.", "ifm.", "ift.", "iht.", "ill.",
+        "indb.", "indreg.", "inf.", "ing.", "inh.", "inj.", "inkl.", "insp.",
+        "instr.", "isl.", "istf.", "it.", "ital.", "iv.", "jap.", "jf.", "jfr.",
+        "jnr.", "j.nr.", "jr.", "jur.", "jvf.", "K.", "kap.", "kat.", "kbh.",
+        "kem.", "kgl.", "kl.", "kld.", "knsp.", "komm.", "kons.", "korr.",
+        "kp.", "Kprs.", "kr.", "kst.", "kt.", "ktr.", "kv.", "kvt.", "l.",
+        "L.A.", "l.c.", "lab.", "lat.", "lb.m.", "lb.nr.", "lejl.", "lgd.",
+        "lic.", "lign.", "lin.", "ling.merc.", "litt.", "Ll.", "loc.cit.",
+        "lok.", "lrs.", "ltr.", "m/s", "M/S", "m.a.o.", "m.fl.", "m.m.", "m.v.",
+        "m.v.h.", "Mag.", "maks.", "md.", "mdr.", "mdtl.", "mezz.", "mfl.",
+        "m.h.p.", "m.h.t", "mht.", "mik.", "min.", "mio.", "modt.", "Mr.",
+        "mrk.", "mul.", "mv.", "n.br.", "n.f.", "nat.", "nb.", "Ndr.",
+        "nedenst.", "nl.", "nr.", "Nr.", "nto.", "nuv.", "o/m", "o.a.", "o.fl.",
+        "o.h.", "o.l.", "o.lign.", "o.m.a.", "o.s.fr.", "obl.", "obs.",
+        "odont.", "oecon.", "off.", "ofl.", "omg.", "omkr.", "omr.", "omtr.",
+        "opg.", "opl.", "opr.", "org.", "orig.", "osv.", "ovenst.", "overs.",
+        "ovf.", "p.", "p.a.", "p.b.a", "p.b.v", "p.c.", "p.m.", "p.m.v.",
+        "p.n.", "p.p.", "p.p.s.", "p.s.", "p.t.", "p.v.a.", "p.v.c.", "pag.",
+        "par.", "Pas.", "pass.", "pcs.", "pct.", "pd.", "pens.", "pers.",
+        "pft.", "pg.", "pga.", "pgl.", "Ph.d.", "pinx.", "pk.", "pkt.",
+        "polit.", "polyt.", "pos.", "pp.", "ppm.", "pr.", "prc.", "priv.",
+        "prod.", "prof.", "pron.", "Prs.", "præd.", "præf.", "præt.", "psych.",
+        "pt.", "pæd.", "q.e.d.", "rad.", "Rcp.", "red.", "ref.", "reg.",
+        "regn.", "rel.", "rep.", "repr.", "resp.", "rest.", "rm.", "rtg.",
+        "russ.", "s.", "s.br.", "s.d.", "s.f.", "s.m.b.a.", "s.u.", "s.å.",
+        "sa.", "sb.", "sc.", "scient.", "scil.", "Sdr.", "sek.", "sekr.",
+        "self.", "sem.", "sen.", "shj.", "sign.", "sing.", "sj.", "skr.",
+        "Skt.", "slutn.", "sml.", "smp.", "sms.", "snr.", "soc.", "soc.dem.",
+        "sort.", "sp.", "spec.", "Spl.", "spm.", "spr.", "spsk.", "statsaut.",
+        "st.", "stk.", "str.", "stud.", "subj.", "subst.", "suff.", "sup.",
+        "suppl.", "sv.", "såk.", "sædv.", "sø.", "t/r", "t.", "t.h.", "t.o.",
+        "t.o.m.", "t.v.", "tab.", "tbl.", "tcp/ip", "td.", "tdl.", "tdr.",
+        "techn.", "tekn.", "temp.", "th.", "theol.", "ti.", "tidl.", "tilf.",
+        "tilh.", "till.", "tilsv.", "tjg.", "tkr.", "tlf.", "tlgr.", "to.",
+        "tr.", "trp.", "tsk.", "tv.", "ty.", "u/b", "udb.", "udbet.", "ugtl.",
+        "undt.", "v.", "v.f.", "var.", "vb.", "vedk.", "vedl.", "vedr.",
+        "vejl.", "Vg.", "vh.", "vha.", "vs.", "vsa.", "vær.", "zool.", "ø.lgd.",
+        "øv.", "øvr.", "årg.", "årh.", ""]:
     _exc[orth] = [{ORTH: orth}]
 
+# Dates
+for h in range(1, 31 + 1):
+    for period in ["."]:
+        _exc["%d%s" % (h, period)] = [
+            {ORTH: "%d." % h}]
+
+_custom_base_exc = {
+    "i.": [
+        {ORTH: "i", LEMMA: "i", NORM: "i"},
+        {ORTH: ".", TAG: PUNCT}]
+}
+_exc.update(_custom_base_exc)
+
 
 TOKENIZER_EXCEPTIONS = _exc

spacy/tests/lang/da/test_exceptions.py

@@ -3,13 +3,31 @@ from __future__ import unicode_literals
 
 import pytest
 
-@pytest.mark.parametrize('text', ["ca.", "m.a.o.", "Jan.", "Dec."])
+@pytest.mark.parametrize('text',
+                         ["ca.", "m.a.o.", "Jan.", "Dec.", "kr.", "jf."])
 def test_da_tokenizer_handles_abbr(da_tokenizer, text):
     tokens = da_tokenizer(text)
     assert len(tokens) == 1
 
+@pytest.mark.parametrize('text', ["Jul.", "jul.", "Tor.", "Tors."])
+def test_da_tokenizer_handles_ambiguous_abbr(da_tokenizer, text):
+    tokens = da_tokenizer(text)
+    assert len(tokens) == 2
+
+@pytest.mark.parametrize('text', ["1.", "10.", "31."])
+def test_da_tokenizer_handles_dates(da_tokenizer, text):
+    tokens = da_tokenizer(text)
+    assert len(tokens) == 1
+
 def test_da_tokenizer_handles_exc_in_text(da_tokenizer):
     text = "Det er bl.a. ikke meningen"
     tokens = da_tokenizer(text)
     assert len(tokens) == 5
     assert tokens[2].text == "bl.a."
+
+def test_da_tokenizer_handles_custom_base_exc(da_tokenizer):
+    text = "Her er noget du kan kigge i."
+    tokens = da_tokenizer(text)
+    assert len(tokens) == 8
+    assert tokens[6].text == "i"
+    assert tokens[7].text == "."