170 | {% block body %}{% endblock %}
171 |
172 | {% if self.comments()|trim %}
173 |
174 | {% block comments %}{% endblock %}
175 |
176 | {% endif%}
177 |
2 |  }}){kind=logo}
3 |
6 | 8 |
9 | 10 | 11 |12 | TextBlob is a Python (2 and 3) library for processing textual data. It provides a consistent API for diving into common natural language processing (NLP) tasks such as part-of-speech tagging, noun phrase extraction, sentiment analysis, and more. 13 |
14 | 15 | 16 |Useful Links
17 |-
18 |
- TextBlob @ PyPI 19 |
- TextBlob @ GitHub 20 |
- Issue Tracker 21 |
4 |
5 | Read the Docs
6 | v: {{ current_version }}
7 |
8 |
9 |
36 | {% endif %}
37 |
38 |
--------------------------------------------------------------------------------
/NOTICE:
--------------------------------------------------------------------------------
1 | textblob-de includes some vendorized libraries, including parts of pattern.
2 |
3 | Pattern License
4 | ===============
5 |
6 | Copyright (c) 2011-2013 University of Antwerp, Belgium
7 | All rights reserved.
8 |
9 | Redistribution and use in source and binary forms, with or without
10 | modification, are permitted provided that the following conditions are met:
11 |
12 | * Redistributions of source code must retain the above copyright
13 | notice, this list of conditions and the following disclaimer.
14 | * Redistributions in binary form must reproduce the above copyright
15 | notice, this list of conditions and the following disclaimer in
16 | the documentation and/or other materials provided with the
17 | distribution.
18 | * Neither the name of Pattern nor the names of its
19 | contributors may be used to endorse or promote products
20 | derived from this software without specific prior written
21 | permission.
22 |
23 | THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
24 | "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
25 | LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
26 | FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE
27 | COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
28 | INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
29 | BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
30 | LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
31 | CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
32 | LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
33 | ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
34 | POSSIBILITY OF SUCH DAMAGE.
35 |
--------------------------------------------------------------------------------
/docs/src/_themes/sphinx_rtd_theme/search.html:
--------------------------------------------------------------------------------
1 | {#
2 | basic/search.html
3 | ~~~~~~~~~~~~~~~~~
4 |
5 | Template for the search page.
6 |
7 | :copyright: Copyright 2007-2013 by the Sphinx team, see AUTHORS.
8 | :license: BSD, see LICENSE for details.
9 | #}
10 | {%- extends "layout.html" %}
11 | {% set title = _('Search') %}
12 | {% set script_files = script_files + ['_static/searchtools.js'] %}
13 | {% block footer %}
14 |
17 | {# this is used when loading the search index using $.ajax fails,
18 | such as on Chrome for documents on localhost #}
19 |
20 | {{ super() }}
21 | {% endblock %}
22 | {% block body %}
23 |
31 |
32 | {% if search_performed %}
33 |
10 |
32 | {% trans %}Free document hosting provided by Read the Docs.{% endtrans %} 33 | 34 |
35 | -
11 |
- {{ _('Versions') }} 12 | {% for slug, url in versions %} 13 |
- {{ slug }} 14 | {% endfor %} 15 |
-
17 |
- {{ _('Downloads') }} 18 | {% for type, url in downloads %} 19 |
- {{ type }} 20 | {% endfor %} 21 |
-
23 |
- {{ _('On Read the Docs') }} 24 |
- 25 | {{ _('Project Home') }} 26 | 27 |
- 28 | {{ _('Builds') }} 29 | 30 |
32 | {% trans %}Free document hosting provided by Read the Docs.{% endtrans %} 33 | 34 |
{{ _('Search Results') }}
34 | {% if not search_results %} 35 |{{ _('Your search did not match any documents. Please make sure that all words are spelled correctly and that you\'ve selected enough categories.') }}
36 | {% endif %} 37 | {% endif %} 38 |
39 | {% if search_results %}
40 |
50 | {% endblock %}
51 |
--------------------------------------------------------------------------------
/docs/src/make_info.rst:
--------------------------------------------------------------------------------
1 | ``make`` command
2 | ----------------
3 |
4 | This project adopts the ``Makefile`` approach, proposed by Jeff Knupp in his
5 | blog post `Open Sourcing a Python Project the Right Way \
6 | -
41 | {% for href, caption, context in search_results %}
42 |
-
43 | {{ caption }}
44 |
{{ context|e }}
45 |
46 | {% endfor %}
47 |
2 |
3 |
6 | 8 |
9 | 10 |11 | TextBlob is a Python (2 and 3) library for processing textual data. It provides a consistent API for diving into common natural language processing (NLP) tasks such as part-of-speech tagging, noun phrase extraction, sentiment analysis, and more. 12 |
13 | 14 | 15 |Useful Links
16 |-
17 |
- TextBlob @ PyPI 18 |
- TextBlob @ GitHub 19 |
- Issue Tracker 20 |
Stay Informed
23 | 24 | 26 | 27 |Donate
28 | 29 |If you find TextBlob useful, please consider supporting its author:
30 | 31 |32 | 35 |
36 | 37 |
38 | 
39 |
Your donation helps move TextBlob forward.
-------------------------------------------------------------------------------- /tests/test_np_extractors.py: -------------------------------------------------------------------------------- 1 | # -*- coding: utf-8 -*- 2 | """Test cases for np extractors.""" 3 | from __future__ import unicode_literals 4 | import unittest 5 | from nose.tools import * # PEP8 asserts 6 | 7 | from textblob_de import PatternParserNPExtractor, NLTKPunktTokenizer 8 | 9 | 10 | class TestPatternParserNPExtractor(unittest.TestCase): 11 | 12 | def setUp(self): 13 | self.extractor = PatternParserNPExtractor( 14 | tokenizer=NLTKPunktTokenizer()) 15 | self.text = "Peter hat ein schönes Auto. Er wohnt in Zürich. " \ 16 | "Seine zwei Katzen heissen Tim und Struppi." 17 | 18 | self.parsed_sentences_expected = [ 19 | 'Peter/NNP/B-NP/O hat/VB/B-VP/O ein/DT/B-NP/O ' 20 | 'schönes/JJ/I-NP/O Auto/NN/I-NP/O ././O/O', 21 | 'Er/PRP/B-NP/O wohnt/NN/I-NP/O in/IN/B-PP/B-PNP ' 22 | 'Zürich/NNP/B-NP/I-PNP ././O/O', 'Seine/PRP$/B-NP/O ' 23 | 'zwei/CD/I-NP/O Katzen/NNS/I-NP/O heissen/VB/B-VP/O ' 24 | 'Tim/NNP/B-NP/O und/CC/I-NP/O Struppi/NNP/I-NP/O ././O/O'] 25 | 26 | def test_parse_text(self): 27 | assert_equal( 28 | self.extractor._parse_text( 29 | self.text), 30 | self.parsed_sentences_expected) 31 | 32 | def test_extract(self): 33 | noun_phrases = self.extractor.extract(self.text) 34 | assert_true("Peter" in noun_phrases) 35 | assert_true("schönes Auto" in noun_phrases) 36 | # only words tagged as nouns are capitalized other words are normalised 37 | assert_true("er" in noun_phrases) 38 | assert_true("Zürich" in noun_phrases) 39 | # added 'und'/'oder' to noun phrase splitters and insignificant 40 | assert_false("Tim und Struppi" in noun_phrases) 41 | 42 | if __name__ == '__main__': 43 | unittest.main() 44 | -------------------------------------------------------------------------------- /docs/src/api_reference.rst: -------------------------------------------------------------------------------- 1 | .. _api: 2 | 3 | API Reference 4 | ============= 5 | 6 | Blob Classes 7 | ------------ 8 | 9 | .. automodule:: textblob_de.blob 10 | :members: 11 | :inherited-members: 12 | 13 | .. _api_base_classes: 14 | 15 | Base Classes 16 | ------------ 17 | 18 | .. automodule:: textblob_de.base 19 | :members: 20 | 21 | Tokenizers 22 | ---------- 23 | 24 | .. automodule:: textblob_de.tokenizers 25 | :members: 26 | :inherited-members: 27 | 28 | POS Taggers 29 | ----------- 30 | 31 | .. automodule:: textblob_de.taggers 32 | :members: 33 | :inherited-members: 34 | 35 | Noun Phrase Extractors 36 | ---------------------- 37 | 38 | .. automodule:: textblob_de.np_extractors 39 | :members: BaseNPExtractor, ConllExtractor, FastNPExtractor 40 | :inherited-members: 41 | 42 | 43 | Sentiment Analyzers 44 | ------------------- 45 | 46 | .. automodule:: textblob_de.sentiments 47 | :members: 48 | :inherited-members: 49 | 50 | 51 | Parsers 52 | ------- 53 | 54 | .. automodule:: textblob_de.parsers 55 | :members: 56 | :inherited-members: 57 | 58 | .. _api_classifiers: 59 | 60 | Classifiers (from `TextBlob`_ main package) 61 | ------------------------------------------- 62 | 63 | .. automodule:: textblob.classifiers 64 | :members: 65 | :inherited-members: 66 | 67 | Blobber 68 | ------- 69 | 70 | .. autoclass:: textblob_de.blob.BlobberDE 71 | :members: 72 | :special-members: 73 | :exclude-members: __weakref__ 74 | 75 | File Formats (from `TextBlob`_ main package) 76 | -------------------------------------------- 77 | 78 | .. automodule:: textblob.formats 79 | :members: 80 | :inherited-members: 81 | 82 | 83 | Exceptions (from `TextBlob`_ main package) 84 | ------------------------------------------ 85 | .. module:: textblob.exceptions 86 | 87 | .. autoexception:: textblob.exceptions.MissingCorpusException 88 | 89 | 90 | .. _TextBlob: http://textblob.readthedocs.org/ 91 | 92 | -------------------------------------------------------------------------------- /docs/src/_themes/sphinx_rtd_theme/footer.html: -------------------------------------------------------------------------------- 1 | 52 | 53 | -------------------------------------------------------------------------------- /tests/test_parsers.py: -------------------------------------------------------------------------------- 1 | # -*- coding: utf-8 -*- 2 | # Code adapted from the main `TextBlob`_ library. 3 | # 4 | # :repo: `https://github.com/sloria/TextBlob`_ 5 | # :source: tests/test_parsers.py 6 | # :version: 2013-10-21 (a88e86a76a) 7 | # 8 | # :modified: 2014-08-29
51 |
84 | {%- endif %}
85 | {%- endmacro %}
86 |
87 | {%- macro script() %}
88 |
98 | {%- for scriptfile in script_files %}
99 |
100 | {%- endfor %}
101 | {%- endmacro %}
102 |
103 | {%- macro css() %}
104 |
105 |
106 | {%- for cssfile in css_files %}
107 |
108 | {%- endfor %}
109 | {%- endmacro %}
110 |
111 |
112 |
113 |
114 | {{ metatags }}
115 | {%- block htmltitle %}
116 |
52 | {%- block sidebarlogo %}
53 | {%- if logo %}
54 |
57 | {%- endif %}
58 | {%- endblock %}
59 | {%- if sidebars != None %}
60 | {#- new style sidebar: explicitly include/exclude templates #}
61 | {%- for sidebartemplate in sidebars %}
62 | {%- include sidebartemplate %}
63 | {%- endfor %}
64 | {%- else %}
65 | {#- old style sidebars: using blocks -- should be deprecated #}
66 | {%- block sidebartoc %}
67 | {%- include "localtoc.html" %}
68 | {%- endblock %}
69 | {%- block sidebarrel %}
70 | {%- include "relations.html" %}
71 | {%- endblock %}
72 | {%- block sidebarsourcelink %}
73 | {%- include "sourcelink.html" %}
74 | {%- endblock %}
75 | {%- if customsidebar %}
76 | {%- include customsidebar %}
77 | {%- endif %}
78 | {%- block sidebarsearch %}
79 | {%- include "searchbox.html" %}
80 | {%- endblock %}
81 | {%- endif %}
82 |
83 |
165 | {%- block document %}
166 |
182 | {%- endblock %}
183 |
184 | {%- block relbar2 %}{{ relbar() }}{% endblock %}
185 |
186 | {%- block footer %}
187 |
202 |
167 | {%- if render_sidebar %}
168 |
177 | {%- endblock %}
178 |
179 | {%- block sidebar2 %}{{ sidebar() }}{% endblock %}
180 |
181 |
169 | {%- endif %}
170 |
175 | {%- endif %}
176 |
171 | {% block body %} {% endblock %}
172 |
173 | {%- if render_sidebar %}
174 | asdf asdf asdf asdf 22
203 | {%- endblock %} 204 | 205 | 206 | 207 | -------------------------------------------------------------------------------- /textblob_de/ext/_pattern/text/de/de-morphology.txt: -------------------------------------------------------------------------------- 1 | XX e fchar ADJA 926.737301587302 2 | ADJA t fhassuf 1 VVPP 245.959523809524 3 | XX e fchar ADJA 968.372222222222 4 | ADJA t fhassuf 1 VVPP 244.85 5 | XX 1 fchar CARDNUM 130.4 6 | ADJA . fgoodleft VVINF 112.697421269564 7 | - hassuf 1 TRUNC 91 8 | XX i fchar ADJD 60 9 | XX 0 fchar CARDNUM 58.9333333333333 10 | sich goodleft VVFIN 46.8139830308869 11 | sche hassuf 4 ADJA 45 12 | NN Dr. fgoodright NE 40 13 | ADJA e faddsuf 1 ADJD 37.75 14 | XX 2 fchar CARDNUM 32 15 | XX t fchar VVFIN 30 16 | ADJA die fgoodleft VVFIN 29.3333333333333 17 | VVPP die fgoodleft VVFIN 24.2666666666667 18 | ig hassuf 2 ADJD 24 19 | . hassuf 1 ADJA 20.2 20 | XX 5 fchar CARDNUM 20 21 | lich hassuf 4 ADJD 19 22 | ADJA zu fgoodright VVINF 18.0166666666667 23 | ) char LINUM 18 24 | < char SGML 16.0041666666667 25 | Ü char NN 16 26 | ADJA werden fgoodleft VVPP 15.5 27 | XX 3 fchar CARDNUM 15 28 | ist goodright ADV 14.2858158208037 29 | einem goodleft APPR 13.9597235705344 30 | worden goodleft VVPP 13.5 31 | ADJD t fhassuf 1 VVFIN 13 32 | ADJA der fgoodleft VVFIN 12 33 | asse hassuf 4 NE 12 34 | da haspref 2 PAV 11.9545454545455 35 | NN chen fhassuf 4 ADJA 11 36 | end hassuf 3 ADJD 11 37 | VVINF en faddsuf 2 VVPP 10.9874686716792 38 | bar hassuf 3 ADJD 10 39 | isch hassuf 4 ADJD 10 40 | XX 4 fchar CARDNUM 10 41 | Prof. goodright NE 9.99583333333333 42 | XX a fchar ADV 9.33333333333333 43 | Ä char NN 8 44 | ADJA im fgoodleft VVFIN 8 45 | ADJA ns fhassuf 2 ADV 7.85714285714286 46 | ADJA - fhaspref 1 NN 7 47 | S hassuf 1 NE 7 48 | NN Hans fgoodright NE 7 49 | VVINF werden fgoodleft VVPP 6.44444444444444 50 | VVFIN werden fgoodright VMFIN 6.43508771929825 51 | er addpref 2 VVFIN 6.4 52 | VVINF en fdeletesuf 2 ADJA 7 53 | VVINF z fchar VVIZU 7 54 | VVIZU zu fgoodright VVINF 11 55 | VVPP der fgoodleft VVFIN 6.4 56 | ADJA . fgoodleft VVFIN 6.07142857142857 57 | ADJA l fhassuf 1 ADJD 6 58 | dem addsuf 3 APPR 6 59 | s addpref 1 ARTIND 5.84673984272608 60 | VVPP auch fgoodleft VVFIN 5.27777777777778 61 | wir goodleft VVFIN 5.26041666666667 62 | s deletepref 1 PPOSAT 5.15789473684211 63 | Ö char NN 5 64 | NN r fdeletesuf 1 ADJA 5 65 | ADJA sie fgoodleft VVFIN 5 66 | ADJA fen fhassuf 3 VVPP 5 67 | VVPP l fhaspref 1 VVFIN 5 68 | NN ann fhassuf 3 NE 5 69 | rich hassuf 4 NE 5 70 | ADJA nicht fgoodleft ADV 5 71 | ADJA ken fhassuf 3 VVINF 5 72 | abzu haspref 4 VVIZU 5 73 | Da deletepref 2 PAV 5 74 | ih haspref 2 PPOSAT 5 75 | uns haspref 3 PPOSAT 5 76 | VVFIN " fgoodleft ARTDEF 4.84444430354394 77 | VVINF e fhassuf 1 VVFIN 4.71372549019608 78 | VVFIN werden fgoodright VMFIN 5.84199584199584 79 | I hassuf 1 NE 4.5 80 | VVFIN r fhassuf 1 ADV 4.44444444444444 81 | ADJA der fgoodleft NN 4 82 | hes hassuf 3 ADJA 4 83 | alen hassuf 4 ADJA 4 84 | iche hassuf 4 ADJA 4 85 | eht hassuf 3 VVFIN 4 86 | ADJA insgesamt fgoodleft VVFIN 4 87 | VVPP man fgoodleft VVFIN 4 88 | ADJA Wir fgoodright VVFIN 4 89 | VVINF ang fhaspref 3 VVPP 4 90 | H hassuf 1 NE 4 91 | T hassuf 1 NE 4 92 | V hassuf 1 NE 4 93 | Z hassuf 1 NE 4 94 | rg hassuf 2 NE 4 95 | ADJA immer fgoodright ADJD 4 96 | XX 9 fchar CARDNUM 4 97 | eb haspref 2 ADV 4 98 | VVFIN sen fhassuf 3 VVINF 4 99 | gabe addsuf 4 APPR 4 100 | XX o fchar FM 4 101 | anz haspref 3 VVIZU 4 102 | dem deletesuf 3 PAV 4 103 | VVFIN des fgoodleft APPR 3.68518518518519 104 | VVPP it fhassuf 2 ADJD 3.66666666666667 105 | je deletepref 2 PIAT 3.66666666666667 106 | VVPP ver fdeletepref 3 VVFIN 3.33333333333333 107 | ADJD des fgoodleft APPR 3.25 108 | CARDNUM . fchar LINUM 3.15804002760524 109 | gewählt goodright VAFIN 3.08424815695397 110 | ADJA F fchar NN 3 111 | ADV A fchar NN 3 112 | ADV ein fgoodright NN 3 113 | VVFIN de fhassuf 2 ADJA 3 114 | äre hassuf 3 ADJA 3 115 | VVFIN die fgoodright ADJA 3 116 | erl haspref 3 VVFIN 3 117 | ADJA mmen fhassuf 4 VVFIN 3 118 | ADJA wiederum fgoodleft VVFIN 3 119 | VVPP das fgoodleft VVFIN 3 120 | ADJD en fhassuf 2 VVPP 3 121 | NN gt fhassuf 2 VVPP 3 122 | ADJA esen fhassuf 4 VVPP 3 123 | A hassuf 1 NE 3 124 | K hassuf 1 NE 3 125 | tein hassuf 4 NE 3 126 | NN iger fhassuf 4 NE 3 127 | nn deletesuf 2 ADV 3 128 | ADJA hr fhassuf 2 ADV 3 129 | mal deletesuf 3 ADV 3 130 | lls hassuf 3 ADV 3 131 | ADJA in fgoodleft ADV 3 132 | VVFIN hat fgoodright ADV 3 133 | VMFIN die fgoodright ADV 3 134 | ADJA kann fgoodleft VVINF 3 135 | ADJA wird fgoodleft VVINF 3 136 | c hassuf 1 FM 3 137 | nige hassuf 4 PIAT 3 138 | kö haspref 2 VMFIN 3 139 | S deletepref 1 PPOSAT 3 140 | ADV Studium fgoodleft APPRART 3 141 | ADV en faddsuf 2 VVFIN 2.9469696969697 142 | ADV e faddsuf 1 ADJD 3.33333333333333 143 | VVFIN em faddsuf 2 ADJD 2.9047619047619 144 | iben hassuf 4 VVFIN 2.83333333333333 145 | da addpref 2 APPR 2.80864197530864 146 | VVINF der fgoodright ADJA 2.73333333333333 147 | ADJA mal faddsuf 3 CARD 3 148 | NN Hochschulen fgoodleft ADJA 2.70652173913043 149 | ADV di fhaspref 2 PDAT 2.54365079365079 150 | VVIZU o fchar VVPP 2.5 151 | VVPP ein fgoodleft ADV 2.5 152 | vorz haspref 4 VVIZU 3 153 | wo deletepref 2 PWAV 2.5 154 | welc haspref 4 PRELS 2.4078431372549 155 | VVINF im fgoodleft VVFIN 2.2952380952381 156 | VVFIN Irchel fgoodright VAFIN 3.14748265433197 157 | VVFIN sind fgoodleft VVPP 2.25 158 | lich hassuf 4 ADJD 2.25 159 | bei deletepref 3 PIAT 2.15 160 | wenn goodleft KON 2.05813439434129 161 | VVFIN W fchar NN 2 162 | - deletepref 1 NN 2 163 | ADJA sich fgoodleft NN 2 164 | NE der fgoodleft NN 2 165 | ADJA Franken fgoodleft NN 2 166 | VVINF m fdeletesuf 1 ADJA 2 167 | PAV e fhassuf 1 ADJA 2 168 | Wic haspref 3 ADJA 2 169 | bare hassuf 4 ADJA 2 170 | iale hassuf 4 ADJA 2 171 | Allg haspref 4 ADJA 2 172 | XX c fchar VVFIN 2 173 | FM g fchar VVFIN 2 174 | VVPP t fdeletesuf 1 VVFIN 2 175 | ADJA er fdeletepref 2 VVFIN 2 176 | ADJA rn fhassuf 2 VVFIN 2 177 | VVPP sc fhaspref 2 VVFIN 2 178 | ADJA hme fhassuf 3 VVFIN 2 179 | tes haspref 3 VVFIN 2 180 | exi haspref 3 VVFIN 2 181 | dau haspref 3 VVFIN 2 182 | VVPP bed fhaspref 3 VVFIN 2 183 | ADJA res fhaspref 3 VVFIN 2 184 | elen hassuf 4 VVFIN 2 185 | ADJA ehen fhassuf 4 VVFIN 2 186 | begi haspref 4 VVFIN 2 187 | ADJA de faddsuf 2 VVFIN 2 188 | ADJA ver faddpref 3 VVFIN 2 189 | VVFIN h faddpref 1 ADJA 2 190 | ADJA folgende fgoodleft VVFIN 2 191 | ADJA er fgoodleft VVFIN 2 192 | ADJA den fgoodleft VVFIN 2 193 | VVPP nicht fgoodleft VVFIN 2 194 | ADJA Er fgoodright VVFIN 2 195 | VVINF eben fhassuf 4 VVPP 2 196 | darg haspref 4 VVPP 2 197 | beig haspref 4 VVPP 2 198 | NN Universität fgoodright NE 2.33333333333333 199 | ung hassuf 3 NN 3 200 | O hassuf 1 NE 2 201 | P hassuf 1 NE 2 202 | W hassuf 1 NE 2 203 | NN y fhassuf 1 NE 2 204 | zi hassuf 2 NE 2 205 | lm hassuf 2 NE 2 206 | sh hassuf 2 NE 2 207 | NN rd fhassuf 2 NE 2 208 | NN dt fhassuf 2 NE 2 209 | Gi haspref 2 NE 2 210 | NN art fhassuf 3 NE 2 211 | Bus haspref 3 NE 2 212 | Gal haspref 3 NE 2 213 | Bas haspref 3 NE 2 214 | NN ener fhassuf 4 NE 2 215 | Schn haspref 4 NE 2 216 | NN Gebäude fgoodright NE 2 217 | ADJA v fhassuf 1 ADJD 2 218 | am hassuf 2 ADJD 2 219 | ig hassuf 2 ADJD 2 220 | wer hassuf 3 ADJD 2 221 | VVFIN ant fhassuf 3 ADJD 2 222 | ADV sch fhassuf 3 ADJD 2 223 | VVPP ent fhassuf 3 ADJD 2 224 | ADJA hter fhassuf 4 ADJD 2 225 | VVFIN echt fhassuf 4 ADJD 2 226 | land addsuf 4 ADJD 2 227 | XX 6 fchar CARDNUM 2 228 | NN Fakultät fgoodright CARDNUM 2 229 | XX n fchar ADV 2 230 | st deletesuf 2 ADV 2 231 | hl deletesuf 2 ADV 2 232 | so hassuf 2 ADV 2 233 | ADJA ts fhassuf 2 ADV 2 234 | VVFIN se fhassuf 2 ADV 2 235 | VVFIN ei fhaspref 2 ADV 2 236 | NN Je fhaspref 2 ADV 2 237 | ies hassuf 3 ADV 2 238 | upt hassuf 3 ADV 2 239 | och hassuf 3 ADV 2 240 | nig hassuf 3 ADV 2 241 | ADJD frü fhaspref 3 ADV 2 242 | Viel deletepref 4 ADV 2 243 | mals hassuf 4 ADV 2 244 | nsam hassuf 4 ADV 2 245 | natü haspref 4 ADV 2 246 | ADJD sondern fgoodright ADV 2 247 | VVFIN sehr fgoodright ADV 2 248 | ADJA ühen fhassuf 4 VVINF 2 249 | ADJD A fchar APPR 2 250 | XX . fchar APPR 2 251 | ADJA ls fhassuf 2 APPR 2 252 | äss hassuf 3 APPR 2 253 | ink haspref 3 APPR 2 254 | ADV des fgoodleft APPR 2 255 | VVFIN einer fgoodleft APPR 2 256 | NN é fchar FM 2 257 | ty hassuf 2 FM 2 258 | ADJA ur fhassuf 2 FM 2 259 | ADJA ce fhassuf 2 FM 2 260 | cus hassuf 3 FM 2 261 | ing hassuf 3 FM 2 262 | ling hassuf 4 NN 2 263 | ces hassuf 3 FM 2 264 | put hassuf 3 FM 2 265 | ions hassuf 4 FM 2 266 | arch hassuf 4 FM 2 267 | Public goodleft FM 2 268 | Dar deletepref 3 PAV 2 269 | manc haspref 4 PIAT 2 270 | eini haspref 4 PIAT 2 271 | wol haspref 3 VMFIN 2 272 | möc haspref 3 VMFIN 2 273 | müs haspref 3 VMFIN 2 274 | ss deletesuf 2 KOUS 2 275 | fern deletesuf 4 KOUS 2 276 | PAV hdem fhassuf 4 KOUS 2 277 | VVFIN als fgoodright KOUS 2 278 | D addpref 1 PPER 2 279 | ADJD dass fgoodright PPER 2 280 | ohl hassuf 3 KON 2 281 | wür deletepref 3 VAFIN 2 282 | ches addsuf 4 PIS 2 283 | eses hassuf 4 PDAT 2 284 | im hassuf 2 APPRART 2 285 | NN anderen fgoodleft APPRART 2 286 | XX S fchar XY 2 287 | wiev haspref 4 PWAT 2 288 | KON c fchar ADV 1.99358974358974 -------------------------------------------------------------------------------- /docs/src/_themes/sphinx_rtd_theme/layout.html: -------------------------------------------------------------------------------- 1 | {# TEMPLATE VAR SETTINGS #} 2 | {%- set url_root = pathto('', 1) %} 3 | {%- if url_root == '#' %}{% set url_root = '' %}{% endif %} 4 | {%- if not embedded and docstitle %} 5 | {%- set titlesuffix = " — "|safe + docstitle|e %} 6 | {%- else %} 7 | {%- set titlesuffix = "" %} 8 | {%- endif %} 9 | {%- set lang_attr = 'en' if language == None else (language | replace('_', '-')) %} 10 | 11 | 12 | 13 | 14 | 15 | 16 | {{ metatags }} 17 | 18 | {% block htmltitle %} 19 |
87 |
88 | {# SIDE NAV, TOGGLES ON MOBILE #}
89 |
147 |
148 |
149 |
150 | {# MOBILE NAV, TRIGGLES SIDE NAV ON TOGGLE #}
151 |
157 |
158 |
159 | `_ for details.
30 |
31 |
32 | Features
33 | --------
34 |
35 | * **NEW:** Works with Python3.7
36 | * All directly accessible ``textblob_de`` classes (e.g. ``Sentence()`` or ``Word()``) are initialized with default models for German
37 | * Properties or methods that do not yet work for German raise a ``NotImplementedError``
38 | * German sentence boundary detection and tokenization (``NLTKPunktTokenizer``)
39 | * Consistent use of specified tokenizer for all tools (``NLTKPunktTokenizer`` or ``PatternTokenizer``)
40 | * Part-of-speech tagging (``PatternTagger``) with keyword ``include_punc=True`` (defaults to ``False``)
41 | * Tagset conversion in ``PatternTagger`` with keyword ``tagset='penn'|'universal'|'stts'`` (defaults to ``penn``)
42 | * Parsing (``PatternParser``) with all ``pattern`` keywords, plus ``pprint=True`` (defaults to ``False``)
43 | * Noun Phrase Extraction (``PatternParserNPExtractor``)
44 | * Lemmatization (``PatternParserLemmatizer``)
45 | * Polarity detection (``PatternAnalyzer``) - Still **EXPERIMENTAL**, does not yet have information on subjectivity
46 | * Full ``pattern.text.de`` API support on Python3
47 | * Supports Python 2 and 3
48 | * See `working features overview `_ for details)::
61 |
62 | $ pip install -U git+https://github.com/markuskiller/textblob-de.git@dev
63 | $ python -m textblob.download_corpora
64 |
65 |
66 | .. note::
67 |
68 | ``TextBlob`` will be installed/upgraded automatically when running
69 | ``pip install``. The second line (``python -m textblob.download_corpora``)
70 | downloads/updates nltk corpora and language models used in ``TextBlob``.
71 |
72 |
73 | Usage
74 | -----
75 |
76 | .. code-block:: python
77 |
78 | >>> from textblob_de import TextBlobDE as TextBlob
79 | >>> text = '''Heute ist der 3. Mai 2014 und Dr. Meier feiert seinen 43. Geburtstag.
80 | Ich muss unbedingt daran denken, Mehl, usw. für einen Kuchen einzukaufen. Aber leider
81 | habe ich nur noch EUR 3.50 in meiner Brieftasche.'''
82 | >>> blob = TextBlob(text)
83 | >>> blob.sentences
84 | [Sentence("Heute ist der 3. Mai 2014 und Dr. Meier feiert seinen 43. Geburtstag."),
85 | Sentence("Ich muss unbedingt daran denken, Mehl, usw. für einen Kuchen einzukaufen."),
86 | Sentence("Aber leider habe ich nur noch EUR 3.50 in meiner Brieftasche.")]
87 | >>> blob.tokens
88 | WordList(['Heute', 'ist', 'der', '3.', 'Mai', ...]
89 | >>> blob.tags
90 | [('Heute', 'RB'), ('ist', 'VB'), ('der', 'DT'), ('3.', 'LS'), ('Mai', 'NN'),
91 | ('2014', 'CD'), ...]
92 | # Default: Only noun_phrases that consist of two or more meaningful parts are displayed.
93 | # Not perfect, but a start (relies heavily on parser accuracy)
94 | >>> blob.noun_phrases
95 | WordList(['Mai 2014', 'Dr. Meier', 'seinen 43. Geburtstag', 'Kuchen einzukaufen',
96 | 'meiner Brieftasche'])
97 |
98 |
99 | .. code-block:: python
100 |
101 | >>> blob = TextBlob("Das Auto ist sehr schön.")
102 | >>> blob.parse()
103 | 'Das/DT/B-NP/O Auto/NN/I-NP/O ist/VB/B-VP/O sehr/RB/B-ADJP/O schön/JJ/I-ADJP/O'
104 | >>> from textblob_de import PatternParser
105 | >>> blob = TextBlobDE("Das ist ein schönes Auto.", parser=PatternParser(pprint=True, lemmata=True))
106 | >>> blob.parse()
107 | WORD TAG CHUNK ROLE ID PNP LEMMA
108 |
109 | Das DT - - - - das
110 | ist VB VP - - - sein
111 | ein DT NP - - - ein
112 | schönes JJ NP ^ - - - schön
113 | Auto NN NP ^ - - - auto
114 | . . - - - - .
115 | >>> from textblob_de import PatternTagger
116 | >>> blob = TextBlob(text, pos_tagger=PatternTagger(include_punc=True))
117 | [('Das', 'DT'), ('Auto', 'NN'), ('ist', 'VB'), ('sehr', 'RB'), ('schön', 'JJ'), ('.', '.')]
118 |
119 |
120 | .. code-block:: python
121 |
122 | >>> blob = TextBlob("Das Auto ist sehr schön.")
123 | >>> blob.sentiment
124 | Sentiment(polarity=1.0, subjectivity=0.0)
125 | >>> blob = TextBlob("Das ist ein hässliches Auto.")
126 | >>> blob.sentiment
127 | Sentiment(polarity=-1.0, subjectivity=0.0)
128 |
129 |
130 | .. warning::
131 |
132 | **WORK IN PROGRESS:** The German polarity lexicon contains only uninflected
133 | forms and there are no subjectivity scores yet. As of version 0.2.3, lemmatized
134 | word forms are submitted to the ``PatternAnalyzer``, increasing the accuracy
135 | of polarity values. New in version 0.2.7: return type of ``.sentiment`` is now
136 | adapted to the main `TextBlob `_.
169 | The only difference is that you will have to prepend an underscore:
170 | ``from _pattern.de import ...``. This is a precautionary measure in case the ``pattern``
171 | library gets native Python3 support in the future.
172 |
173 |
174 | Documentation and API Reference
175 | -------------------------------
176 |
177 | - http://textblob-de.readthedocs.org/en/latest
178 |
179 |
180 | Requirements
181 | ------------
182 |
183 | - Python >= 2.6 or >= 3.3
184 |
185 | TODO
186 | ----
187 |
188 | - `Planned Extensions `_
189 | - Additional PoS tagging options, e.g. NLTK tagging (``NLTKTagger``)
190 | - Improve noun phrase extraction (e.g. based on ``RFTagger`` output)
191 | - Improve sentiment analysis (find suitable subjectivity scores)
192 | - Improve functionality of ``Sentence()`` and ``Word()`` objects
193 | - Adapt more tests from the main `TextBlob `_ file for more details.
200 |
201 |
202 | Thanks
203 | ------
204 |
205 | Coded with Wing IDE (free open source developer license)
206 |
207 | .. image:: https://wingware.com/images/wingware-logo-180x58.png
208 | :target: https://wingware.com/store/free
209 | :alt: Python IDE for Python - wingware.com
210 |
211 |
--------------------------------------------------------------------------------
/docs/src/conf.py:
--------------------------------------------------------------------------------
1 | # -*- coding: utf-8 -*-
2 | #
3 | # textblob documentation build configuration file, created by
4 | # sphinx-quickstart on Mon Aug 5 01:41:33 2013.
5 | #
6 | # This file is execfile()d with the current directory set to its containing dir.
7 | #
8 | # Note that not all possible configuration values are present in this
9 | # autogenerated file.
10 | #
11 | # All configuration values have a default; values that are commented out
12 | # serve to show the default.
13 |
14 | import sys, os
15 |
16 | # If extensions (or modules to document with autodoc) are in another directory,
17 | # add these directories to sys.path here. If the directory is relative to the
18 | # documentation root, use os.path.abspath to make it absolute, like shown here.
19 | docs_dir = os.path.dirname(__file__)
20 | project_dir = os.path.abspath(os.path.join(docs_dir, '..'))
21 | print(project_dir)
22 | sys.path.insert(1, project_dir)
23 | import textblob_de
24 | sys.path.pop(1)
25 | sys.path.append(os.path.abspath("_themes"))
26 |
27 | # -- General configuration -----------------------------------------------------
28 |
29 | # If your documentation needs a minimal Sphinx version, state it here.
30 | #needs_sphinx = '1.0'
31 |
32 | # Add any Sphinx extension module names here, as strings. They can be extensions
33 | # coming with Sphinx (named 'sphinx.ext.*') or your custom ones.
34 | extensions = [
35 | 'sphinx.ext.autodoc',
36 | 'sphinx.ext.doctest',
37 | 'sphinx.ext.intersphinx',
38 | 'sphinx.ext.todo',
39 | 'sphinx.ext.coverage',
40 | 'sphinx.ext.viewcode',
41 | ]
42 |
43 | # Add any paths that contain templates here, relative to this directory.
44 | templates_path = ['_templates']
45 |
46 | # The suffix of source filenames.
47 | source_suffix = '.rst'
48 |
49 | # The encoding of source files.
50 | #source_encoding = 'utf-8-sig'
51 |
52 | # The master toctree document.
53 | master_doc = 'index'
54 |
55 | # General information about the project.
56 | project = u'textblob-de'
57 | copyright = u'2014-2019, Markus Killer (http://langui.ch)'
58 |
59 | # The version info for the project you're documenting, acts as replacement for
60 | # |version| and |release|, also used in various other places throughout the
61 | # built documents.
62 | #
63 | # The short X.Y version.
64 | version = release = textblob_de.__version__
65 |
66 | # The language for content autogenerated by Sphinx. Refer to documentation
67 | # for a list of supported languages.
68 | #language = None
69 |
70 | # There are two options for replacing |today|: either, you set today to some
71 | # non-false value, then it is used:
72 | #today = ''
73 | # Else, today_fmt is used as the format for a strftime call.
74 | #today_fmt = '%B %d, %Y'
75 |
76 | # List of patterns, relative to source directory, that match files and
77 | # directories to ignore when looking for source files.
78 | exclude_patterns = ['_build']
79 |
80 | # The reST default role (used for this markup: `text`) to use for all documents.
81 | #default_role = None
82 |
83 | # If true, '()' will be appended to :func: etc. cross-reference text.
84 | #add_function_parentheses = True
85 |
86 | # If true, the current module name will be prepended to all description
87 | # unit titles (such as .. function::).
88 | #add_module_names = True
89 |
90 | # If true, sectionauthor and moduleauthor directives will be shown in the
91 | # output. They are ignored by default.
92 | #show_authors = False
93 |
94 | # The name of the Pygments (syntax highlighting) style to use.
95 | #pygments_style = 'flask_theme_support.FlaskyStyle'
96 |
97 | # A list of ignored prefixes for module index sorting.
98 | #modindex_common_prefix = []
99 |
100 | # If true, keep warnings as "system message" paragraphs in the built documents.
101 | #keep_warnings = False
102 |
103 |
104 | # -- Options for HTML output ---------------------------------------------------
105 |
106 | # The theme to use for HTML and HTML Help pages. See the documentation for
107 | # a list of builtin themes.
108 | html_theme = 'sphinx_rtd_theme'
109 |
110 | # Theme options are theme-specific and customize the look and feel of a theme
111 | # further. For a list of options available for each theme, see the
112 | # documentation.
113 | #html_theme_options = {}
114 |
115 | # Add any paths that contain custom themes here, relative to this directory.
116 | html_theme_path = ['_themes']
117 |
118 | # The name for this set of Sphinx documents. If None, it defaults to
119 | # " v documentation".
120 | #html_title = None
121 |
122 | # A shorter title for the navigation bar. Default is the same as html_title.
123 | #html_short_title = None
124 |
125 | # The name of an image file (relative to this directory) to place at the top
126 | # of the sidebar.
127 | #html_logo = None
128 |
129 | # The name of an image file (within the static path) to use as favicon of the
130 | # docs. This file should be a Windows icon file (.ico) being 16x16 or 32x32
131 | # pixels large.
132 | #html_favicon = None
133 |
134 | # Add any paths that contain custom static files (such as style sheets) here,
135 | # relative to this directory. They are copied after the builtin static files,
136 | # so a file named "default.css" will overwrite the builtin "default.css".
137 | html_static_path = ['_static']
138 |
139 | # If not '', a 'Last updated on:' timestamp is inserted at every page bottom,
140 | # using the given strftime format.
141 | #html_last_updated_fmt = '%b %d, %Y'
142 |
143 | # If true, SmartyPants will be used to convert quotes and dashes to
144 | # typographically correct entities.
145 | #html_use_smartypants = True
146 |
147 | # Custom sidebar templates, maps document names to template names.
148 | #html_sidebars = {
149 | #'index': ['side-primary.html', 'searchbox.html'],
150 | #'**': ['side-secondary.html', 'localtoc.html',
151 | #'relations.html', 'searchbox.html']
152 | #}
153 |
154 | # Additional templates that should be rendered to pages, maps page names to
155 | # template names.
156 | #html_additional_pages = {}
157 |
158 | # If false, no module index is generated.
159 | #html_domain_indices = True
160 |
161 | # If false, no index is generated.
162 | #html_use_index = True
163 |
164 | # If true, the index is split into individual pages for each letter.
165 | #html_split_index = False
166 |
167 | # If true, links to the reST sources are added to the pages.
168 | #html_show_sourcelink = True
169 |
170 | # If true, "Created using Sphinx" is shown in the HTML footer. Default is True.
171 | #html_show_sphinx = True
172 |
173 | # If true, "(C) Copyright ..." is shown in the HTML footer. Default is True.
174 | #html_show_copyright = True
175 |
176 | # If true, an OpenSearch description file will be output, and all pages will
177 | # contain a tag referring to it. The value of this option must be the
178 | # base URL from which the finished HTML is served.
179 | #html_use_opensearch = ''
180 |
181 | # This is the file name suffix for HTML files (e.g. ".xhtml").
182 | #html_file_suffix = None
183 |
184 | # Output file base name for HTML help builder.
185 | htmlhelp_basename = 'textblobdedoc'
186 |
187 |
188 | # -- Options for LaTeX output --------------------------------------------------
189 |
190 | latex_elements = {
191 | # The paper size ('letterpaper' or 'a4paper').
192 | #'papersize': 'letterpaper',
193 |
194 | # The font size ('10pt', '11pt' or '12pt').
195 | #'pointsize': '10pt',
196 |
197 | # Additional stuff for the LaTeX preamble.
198 | #'preamble': '',
199 | }
200 |
201 | # Grouping the document tree into LaTeX files. List of tuples
202 | # (source start file, target name, title, author, documentclass [howto/manual]).
203 | latex_documents = [
204 | ('index', 'textblob-de.tex', u'textblob-de Documentation',
205 | u'Markus Killer', 'manual'),
206 | ]
207 |
208 | # The name of an image file (relative to this directory) to place at the top of
209 | # the title page.
210 | #latex_logo = None
211 |
212 | # For "manual" documents, if this is true, then toplevel headings are parts,
213 | # not chapters.
214 | #latex_use_parts = False
215 |
216 | # If true, show page references after internal links.
217 | #latex_show_pagerefs = False
218 |
219 | # If true, show URL addresses after external links.
220 | #latex_show_urls = False
221 |
222 | # Documents to append as an appendix to all manuals.
223 | #latex_appendices = []
224 |
225 | # If false, no module index is generated.
226 | #latex_domain_indices = True
227 |
228 |
229 | # -- Options for manual page output --------------------------------------------
230 |
231 | # One entry per manual page. List of tuples
232 | # (source start file, name, description, authors, manual section).
233 | man_pages = [
234 | ('index', 'textblob-de', u'textblob-de Documentation',
235 | [u'Markus Killer'], 1)
236 | ]
237 |
238 | # If true, show URL addresses after external links.
239 | #man_show_urls = False
240 |
241 |
242 | # -- Options for Texinfo output ------------------------------------------------
243 |
244 | # Grouping the document tree into Texinfo files. List of tuples
245 | # (source start file, target name, title, author,
246 | # dir menu entry, description, category)
247 | texinfo_documents = [
248 | ('index', 'textblob_de', u'textblob-de Documentation',
249 | u'Markus Killer', 'textblob-de', 'German language extension for TextBlob.',
250 | 'Natural Language Processing'),
251 | ]
252 |
253 | # Documents to append as an appendix to all manuals.
254 | #texinfo_appendices = []
255 |
256 | # If false, no module index is generated.
257 | #texinfo_domain_indices = True
258 |
259 | # How to display URL addresses: 'footnote', 'no', or 'inline'.
260 | #texinfo_show_urls = 'footnote'
261 |
262 | # If true, do not generate a @detailmenu in the "Top" node's menu.
263 | #texinfo_no_detailmenu = False
264 |
--------------------------------------------------------------------------------
/textblob_de/ext/_pattern/text/de/de-context.txt:
--------------------------------------------------------------------------------
1 | PTKZU APPR NEXT1OR2OR3TAG NN
2 | ARTDEF PRELS SURROUNDTAG C APPR
3 | APPR PTKVZ NEXTTAG S
4 | VVFIN VAFIN PREVTAG VVPP
5 | NN NE PREVTAG NE
6 | NN ADJA SURROUNDTAG STAART NN
7 | ARTDEF PRELS NEXTTAG ARTDEF
8 | ARTDEF PRELS SURROUNDTAG C ADV
9 | ADV KON LBIGRAM , aber
10 | APPR KOUI PREVTAG C
11 | VVPP VVFIN NEXT1OR2TAG NN
12 | ADJA VVFIN NEXTTAG C
13 | ARTDEF PRELS SURROUNDTAG C APPRART
14 | PDAT PDS NEXTTAG VVFIN
15 | VVINF VVFIN NEXT1OR2TAG NN
16 | VVFIN VVINF PREVWD zu
17 | KOKOM KON RBIGRAM als auch
18 | ADV PIAT NEXTTAG NN
19 | ADJA VVFIN SURROUNDTAG NN APPR
20 | ARTDEF PDS NEXTTAG VVFIN
21 | APPR PTKVZ NEXTTAG C
22 | PIS ADJA NEXTTAG NN
23 | ARTIND PTKVZ NEXTTAG S
24 | PDAT PRELAT PREV1OR2TAG C
25 | VVFIN VAFIN NEXT1OR2OR3TAG VVPP
26 | ADJA VVFIN NEXTTAG ADV
27 | ARTDEF PRELS SURROUNDTAG C PRF
28 | NE NN CURWD Basis
29 | ADJA VVINF NEXTTAG VMFIN
30 | NN VVPP SURROUNDTAG STAART VAFIN
31 | KOKOM KOUS LBIGRAM , wie
32 | VAFIN VVFIN WDNEXTTAG hat ADV
33 | ADJA VVFIN SURROUNDTAG NN KON
34 | NN ADV SURROUNDTAG STAART VVFIN
35 | NN FM NEXTTAG FM
36 | VMFIN VMINF PREVTAG PTKZU
37 | VVFIN VVPP WDPREVTAG NN verlangt
38 | ADJD ADV WDNEXTTAG hauptsächlich APPR
39 | ARTDEF PRELS SURROUNDTAG C PPER
40 | ADJA NN NEXTTAG VVPP
41 | ADJD VVPP CURWD bezogen
42 | LINUM ADJA WDNEXTTAG 7. NN
43 | FM NN CURWD Information
44 | APPR ADV NEXTTAG KOKOM
45 | VVINF ADJA NEXTTAG NN
46 | VVINF PPOSAT NEXTTAG NN
47 | APPR ADV LBIGRAM wie vor
48 | NN NE PREVWD Offsetdrucke
49 | VVPP VVFIN NEXTTAG PPER
50 | NN NE PREV1OR2WD phil.
51 | VVFIN VVINF NEXT1OR2TAG PTKZU
52 | VVFIN VVPP NEXTTAG VAINF
53 | ADJA VVFIN NEXTTAG PPER
54 | VAINF VAFIN PREVTAG PPER
55 | NN ADJA NEXTBIGRAM NN S
56 | NN ADJA NEXTBIGRAM NN APPR
57 | VVPP ADJD NEXTTAG APPR
58 | PIAT ADJA NEXTTAG NN
59 | VVFIN FM NEXTTAG VVFIN
60 | VVFIN ADV PREV1OR2TAG VVFIN
61 | PTKZU APPR NEXTTAG ARTIND
62 | PRELS PWAT NEXTTAG NN
63 | APPR PTKVZ NEXTTAG KON
64 | VVFIN VAFIN NEXTWD durch
65 | VVFIN VAFIN RBIGRAM sind die
66 | VVPP VVFIN NEXTTAG ADV
67 | NN NE CURWD Europa
68 | VVPP VVFIN NEXT1OR2TAG PAV
69 | VVPP VVFIN CURWD zusammensetzt
70 | VVINF VVFIN PREVTAG PPER
71 | VVFIN VVINF CURWD ablegen
72 | ADJA VVFIN NEXTTAG ARTDEF
73 | VAINF VAFIN NEXTTAG ADV
74 | ARTDEF PRELS SURROUNDTAG C PIAT
75 | VAINF VAFIN PREVBIGRAM ADJA NN
76 | NN ADJA NEXTBIGRAM NN Po
77 | ADJA NN SURROUNDTAG STAART VVFIN
78 | ADV ADJD CURWD leicht
79 | NE NN PREV1OR2TAG ARTIND
80 | ADJA ADV PREVTAG PRF
81 | VVFIN ADJD NEXTTAG ADJA
82 | NE NN NEXT2TAG ADV
83 | ADJA ADV NEXTTAG CARDNUM
84 | ADV VVFIN LBIGRAM STAART Ist
85 | ARTDEF PDS NEXTTAG VVINF
86 | ADV KON WDAND2TAGBFR ADV doch
87 | NN APPR RBIGRAM Innerhalb der
88 | LINUM ADJA NEXTWD Nebenfach
89 | FM NN PREVTAG ADJA
90 | VMFIN VMINF RBIGRAM müssen .
91 | PTKVZ ADV NEXT1OR2OR3TAG ARTDEF
92 | ADJD FM PREV1OR2TAG FM
93 | VVINF ADJD CURWD schwieriger
94 | ARTDEF PDS NEXTTAG VVPP
95 | ADJA LINUM LBIGRAM STAART 6.
96 | FM NN PREV1OR2OR3TAG C
97 | ADV NN CURWD 50-Prozent-Stelle
98 | PTKZU PTKVZ NEXTTAG S
99 | PPER PRF PREVWD wir
100 | VVINF VVFIN NEXT1OR2TAG PRF
101 | VAFIN ADV NEXT1OR2OR3TAG VVPP
102 | PAV VVFIN PREVTAG NN
103 | VVFIN VAFIN RBIGRAM war im
104 | VVFIN VAFIN RBIGRAM sind im
105 | VVFIN VAFIN LBIGRAM ; ist
106 | VVFIN VAFIN LBIGRAM 1994 ist
107 | VVFIN VAFIN NEXT1OR2WD wieder
108 | NN NE RBIGRAM VDM (
109 | VVFIN VAFIN PREV1OR2WD zwei
110 | NN NE NEXT1OR2WD University
111 | VVFIN VAFIN SURROUNDTAG KON APPR
112 | NN NE PREV1OR2WD Jura-Gemeinde
113 | VVFIN VAFIN SURROUNDTAG NN PPOSAT
114 | VVPP VVFIN NEXT1OR2TAG KOKOM
115 | NN NE PREVBIGRAM NE KON
116 | VVFIN VAFIN SURROUNDTAG ADV CARDNUM
117 | VVPP VVFIN PREV1OR2TAG PPOSAT
118 | NN NE NEXTBIGRAM Pc VAFIN
119 | VVFIN VAFIN NEXT2TAG CARD
120 | VVPP VVFIN RBIGRAM entspricht .
121 | NN NE SURROUNDTAG APPR NE
122 | VVFIN VAFIN WDAND2AFT sind für
123 | VVPP VVFIN NEXTBIGRAM KON KOUS
124 | NN NE CURWD Graecum
125 | VVINF VVFIN NEXTTAG ARTDEF
126 | VVFIN VAFIN WDAND2TAGBFR NE ist
127 | VVPP VVFIN NEXTBIGRAM C VVFIN
128 | VAFIN VVFIN PREV1OR2WD mit
129 | NN NE CURWD Latinum
130 | VVINF VVFIN NEXTTAG ADV
131 | VAFIN VVFIN NEXTBIGRAM ADJD C
132 | NN NE CURWD WIF
133 | VVINF VVFIN CURWD fallen
134 | VVFIN VVINF PREVWD dafür
135 | VVFIN VVINF WDPREVTAG NN sprechen
136 | VVFIN VVPP NEXT1OR2WD mit
137 | VVPP VVFIN PREVTAG PPER
138 | VVFIN VVINF WDPREVTAG NN gelten
139 | ADJD ADV NEXT1OR2TAG CARD
140 | VVFIN VVINF PREV1OR2WD mehreren
141 | VVFIN VVPP NEXT1OR2WD hat
142 | ADJD ADV PREV1OR2TAG VVINF
143 | VVFIN VVPP PREV1OR2WD werden
144 | ADJD ADV CURWD letztlich
145 | VVFIN VVPP CURWD bewährt
146 | ADJD ADV CURWD ausschliesslich
147 | ADJA VVFIN NEXTTAG APPRART
148 | ADJA VVFIN NEXTTAG Co
149 | VVFIN VVPP PREVTAG VAFIN
150 | ARTDEF PRELS NEXTWD andere
151 | ADJA VVFIN NEXTBIGRAM ADJD ARTDEF
152 | VVFIN ADJA PREVTAG APPR
153 | ARTDEF PRELS SURROUNDTAG C ADJD
154 | ADJA NN NEXTTAG S
155 | VVFIN ADJA NEXTBIGRAM NN APPR
156 | VVPP ADJD PREV1OR2WD sind
157 | NN ADJA PREV1OR2WD Philologie
158 | NN NE PREVBIGRAM C NN
159 | NN NE NEXTBIGRAM NE C
160 | VAINF VAFIN PREVTAG VVINF
161 | VVPP ADJD CURWD effizienter
162 | NN ADJA SURROUNDTAG QMo NN
163 | NN ADV LBIGRAM STAART Nur
164 | ADV ADJD SURROUNDTAG NN VVFIN
165 | NN ADJA SURROUNDTAG SGML NE
166 | ADJA PIAT LBIGRAM STAART Beide
167 | NN ADV LBIGRAM STAART Besonders
168 | PDAT PDS NEXTTAG VAFIN
169 | NN FM PREVTAG FM
170 | ADJA PIAT CURWD keinerlei
171 | PIDAT PIAT WDPREVTAG APPR beiden
172 | NE NN PREVBIGRAM SGML ADJA
173 | ADV VVFIN NEXTTAG PRF
174 | ADJA ADV NEXTTAG PTKVZ
175 | VVFIN NN PREVTAG ARTIND
176 | VVFIN ADJD WDPREVTAG ADV gross
177 | NN FM NEXT1OR2WD Program
178 | NN ADJD WDNEXTTAG rege VVPP
179 | VVPP VVINF PREVTAG PTKZU
180 | VVINF VVPP WDPREVTAG NN besprochen
181 | ADV VVFIN PREVBIGRAM NN NN
182 | ADJD NN PREVTAG APPRART
183 | VVFIN NN PREV1OR2OR3TAG Po
184 | VVFIN ADJD NEXTBIGRAM C ADJD
185 | NN FM SURROUNDTAG ADJD S
186 | ADV FM NEXTTAG FM
187 | ADJA VVINF NEXTTAG VAFIN
188 | PIAT PIS WDPREVTAG NN einiges
189 | NN APPR RBIGRAM Seitens der
190 | ADJD PTKVZ RBIGRAM bereit ,
191 | ADJD NN CURWD Informationstisch
192 | ADJA PIS RBIGRAM andere als
193 | ADJA NE RBIGRAM uniagenda "
194 | PTKVZ APPR NEXTTAG ARTDEF
195 | PTKVZ ADV NEXT2TAG S
196 | ADV FM PREV1OR2OR3TAG FM
197 | ADJD FM PREVTAG FM
198 | ADJD ADJA NEXTTAG NN
199 | ADJA VVINF NEXTTAG PTKZU
200 | VVINF ADJD NEXTBIGRAM PTKZU VVINF
201 | ADJA PDS WDPREVTAG APPR jenem
202 | APPR PTKA NEXTTAG ADV
203 | ADV PTKVZ NEXTTAG S
204 | ADJA LINUM LBIGRAM STAART 4.
205 | ADJA FM PREVTAG FM
206 | VVIZU ADJA CURWD vorzeitiger
207 | VVINF ADJD CURWD geringer
208 | VVFIN FM CURWD to
209 | PTKZU APPR NEXT1OR2TAG ADJA
210 | PTKVZ APZR WDPREVTAG NN hin
211 | PTKVZ APPR NEXT1OR2TAG APPR
212 | PRELS PDS NEXT1OR2WD Erstsemestrigen
213 | PIDAT PIS PREV1OR2OR3TAG KON
214 | PDS ARTDEF NEXT1OR2TAG ADJA
215 | KOUS ADV PREV1OR2OR3TAG VVFIN
216 | ARTIND PTKVZ NEXTTAG C
217 | ADV NE NEXTTAG KON
218 | ADV ADJA NEXTTAG NN
219 | ADJA VVINF NEXTWD lassen
220 | XX CARDNUM PREV1OR2OR3TAG ARTDEF
221 | XX APPRART NEXTTAG NN
222 | VVINF VAINF PREV1OR2TAG VVPP
223 | VVFIN PPOSAT WDNEXTTAG meine NN
224 | PPER ADJD PREVTAG KOUS
225 | NN VVIMP LBIGRAM STAART S.
226 | KOUS KOKOM NEXT1OR2TAG C
227 | ADV PWAV NEXTTAG PPER
228 | ADJD NE PREV1OR2WD Spalte
229 | ADJA PWAT WDNEXTTAG Welche NN
230 | ADJA PPOSAT LBIGRAM STAART Ihre
231 | ADJA LINUM LBIGRAM STAART 1.
232 | VVFIN VAFIN NEXTWD viereinhalb
233 | PIAT ADV NEXTTAG ADJD
234 | PDS FM NEXTWD academicus
235 | VMFIN VMINF PREVTAG PTKZU
236 | VVFIN VVINF PREVTAG PTKZU
237 | KOUS ADV PREVTAG KON
238 | KOUS ADV PREVTAG KOUS
239 | KON ADV PREVTAG KON
240 | KON ADV PREVTAG KOUS
241 | KON ADV NEXTTAG KOUS
242 | KON ADV PREVTAG NN
243 | ARTIND PIDAT PREVTAG ARTDEF
244 | ARTIND PIDAT PREVTAG APPRART
245 | ARTIND PIS NEXTTAG ARTDEF
246 | ARTDEF PDS NEXTTAG VVPP
247 | ARTDEF PDS NEXTTAG VMFIN
248 | ARTDEF PDS NEXTTAG VVFIN
249 | ARTDEF PDS NEXTTAG VAFIN
250 | ARTDEF PDS NEXTTAG VVINF
251 | ARTDEF PDS NEXTTAG C
252 | VVFIN VAFIN NEXT1OR2OR3TAG VVPP
253 | VVFIN VAFIN PREVTAG VVPP
254 | VVINF VAINF PREV1OR2TAG VVPP
255 | PRELS PDS PREVTAG VVFIN
256 | PTKZU APPR NEXTTAG ARTDEF
257 | PTKZU APPR NEXTTAG ARTIND
258 | PTKZU APPR NEXTTAG ADJA
259 | PTKZU APPR NEXTTAG NN
260 | PTKZU PTKA NEXT1OR2TAG ADV
261 | PTKZU PTKA NEXT1OR2TAG ADJD
262 | VVFIN VVINF PREVTAG APPR
263 | VAFIN VAINF PREVTAG APPR
264 | APPR PTKZU NEXTTAG VVINF
265 | APPR PTKZU NEXTTAG VAINF
266 | APPR PTKVZ NEXTTAG Co
267 | APPR PTKVZ NEXTTAG S
268 | APPR PTKVZ NEXTTAG Se
269 | APPR PTKVZ NEXTTAG KON
270 | KOKOM KOUS NEXT1OR2OR3WD Jahre
271 | VVFIN VVINF NEXTTAG VMFIN
272 | KOKOM PWAV PREVTAG Co
273 | VVFIN VVINF NEXTTAG VVFIN
274 | KOUS ADV PREVTAG VVFIN
275 | KOUS ADV PREVTAG VAFIN
276 | VAINF VAFIN PREVTAG VVINF
277 | VAFIN VAINF NEXTTAG VMFIN
278 | VAINF VAFIN NEXTTAG VVINF
279 | VAINF VAFIN NEXTTAG APPRART
280 | ADV KON PREV1OR2OR3WD weder
281 | VAFIN VVFIN PREVTAG ADJD
282 | KOUS ADV NEXTTAG C
283 | KOUS ADV NEXTTAG S
284 | KOUS ADV NEXTTAG Ex
285 | VVPP VVFIN NEXTTAG PPER
286 | VVPP VVFIN NEXTTAG NN
287 | VVPP VVFIN NEXTTAG ARTDEF
288 | VVPP VVFIN NEXTTAG ARTIND
289 | VVPP VVFIN NEXTTAG ADJA
290 | ADJA ADJD NEXTTAG VVPP
291 | ADJA ADJD NEXTTAG VVFIN
292 | APPRART PTKA NEXTTAG ADJD
293 | PDAT PDS NEXTTAG PPOSAT
294 | PDAT PDS NEXTTAG ARTDEF
295 | PDAT PDS NEXTTAG ARTIND
296 | PDAT PDS NEXTTAG VVFIN
297 | PDAT PDS NEXTTAG VMFIN
298 | PDAT PDS NEXTTAG VAFIN
299 | PDAT PDS NEXTTAG ADV
300 | ARTDEF PRELS SURROUNDTAG APPR PPER
301 | ARTDEF PRELS SURROUNDTAG APPR PIS
302 | ARTDEF PRELS SURROUNDTAG C ARTDEF
303 | ARTDEF PRELS SURROUNDTAG C ARTDIND
304 | ARTDEF PRELS SURROUNDTAG Po ADJD
305 | PIS PIAT NEXTTAG NN
306 | PIAT PIS NEXTTAG C
307 | PIAT PIS NEXTTAG S
308 | PIAT PIS PREVTAG PIS
309 | PIAT PIS NEXTTAG APPR
310 | PIAT PIS NEXTTAG KOKOM
311 | PIAT ADV NEXTTAG VVPP
312 | PIS ADV NEXTTAG VVPP
313 | PIAT PIS NEXTTAG VVPP
314 | PIDAT PIS SURROUNDTAG APPRART VVFIN
315 | PIDAT PIS SURROUNDTAG APPRART VMFIN
316 | PIDAT PIS SURROUNDTAG APPRART APPR
317 | VVINF VVFIN NEXTTAG ADJD
318 | PRELS PWAT PREVTAG KON
319 | PRELAT PWAT PREVTAG APPR
320 | PTKVZ ADJD PREVTAG APPRART
321 | PTKVZ ADJD NEXTTAG VVFIN
322 | PTKZU PTKVZ NEXTTAG S
323 | VVFIN VVINF PREV1OR2OR3TAG VMFIN
324 | APPR KOUS PREVTAG C
325 | APPR APPO NEXTTAG ADV
326 | PPER PPOSAT PREVTAG ARTDEF
327 | PPER PPOSAT PREVTAG ARTIND
328 | VVINF VVIMP NEXTWD Sie
329 | VVFIN VVIMP NEXTWD Sie
330 | APPR KOUS SURROUNDTAG C PPER
331 | PRELAT PDAT PREVTAG NN
332 | PRELAT PRELS NEXTTAG PRF
333 | VVPP ADJD NEXTTAG APPR
334 | ADV PTKVZ NEXTTAG S
335 | ADV PTKVZ NEXTTAG C
336 | ARTIND PTKVZ NEXTTAG C
337 | ARTIND PTKVZ NEXTTAG S
338 | ARTIND PTKVZ NEXTTAG Ex
339 | ARTIND PTKVZ NEXTTAG Co
340 | ARTIND PTKVZ NEXTTAG KOKOM
341 | VVFIN VVPP NEXTTAG VAFIN
342 | VVFIN VVPP NEXTTAG VAINF
343 | VVFIN VVPP NEXTWD von
344 | VVFIN VVPP PREV1OR2TAG VAFIN
345 | VVFIN ADJA PREV1OR2TAG KOKOM
346 | KOKOM KON RBIGRAM als auch
347 | KOKOM KON RBIGRAM wie auch
348 | PAV KOUS LBIGRAM , damit
349 | KOUS KOKOM NEXT1OR2TAG C
350 | PTKVZ ADV NEXTTAG VVPP
351 | PTKVZ APPR NEXTTAG ARTDEF
352 | PTKVZ APPR NEXTTAG ARTIND
353 | PTKVZ APPR NEXTTAG NN
354 | PTKVZ APPR NEXTTAG ADJA
355 | PTKVZ ADV NEXTTAG KOKOM
356 | ADJD VVPP NEXTTAG VAINF
357 | ADJD VVPP NEXTTAG VAFIN
358 | ADV VVPP NEXTTAG VAINF
359 | ADV VVPP NEXTTAG VAFIN
360 | ADV APPR NEXTTAG NN
361 | ADV APPR NEXTTAG TRUNC
362 | VVINF PPOSAT NEXTTAG NN
363 | VVINF VVFIN SURROUNDTAG NN C
364 | VVINF VVFIN PREVTAG PPER
365 | VVPP PTKVZ NEXTTAG S
366 | APPR ADV RBIGRAM nach wie
367 | APPR ADV LBIGRAM wie vor
368 | VVFIN VVINF SURROUNDTAG PPER PTKZU
369 | VVFIN VVINF SURROUNDTAG NN PTKZU
370 | VVINF VVFIN SURROUNDTAG NN APPR
371 | APPR ADV NEXTTAG VVPP
372 | APPR ADV RBIGRAM nach wie
373 | * VVPP NEXTWDTAG worden VAPP
374 | * KON CURWD und
--------------------------------------------------------------------------------
/textblob_de/ext/_pattern/text/de/__init__.py:
--------------------------------------------------------------------------------
1 | #### PATTERN | DE ##################################################################################
2 | # -*- coding: utf-8 -*-
3 | # Copyright (c) 2012 University of Antwerp, Belgium
4 | # Author: Tom De Smedt
5 | # License: BSD (see LICENSE.txt for details).
6 | # http://www.clips.ua.ac.be/pages/pattern
7 |
8 | # Source: https://github.com/clips/pattern/pattern/text/de/__init__.py
9 | # git-commit: 2014-05-10 (eb98cd7)
10 |
11 | # Modified: 2014-08-04 Markus Killer
12 |
13 | ####################################################################################################
14 | # German linguistical tools using fast regular expressions.
15 | from __future__ import absolute_import
16 | import os
17 | import sys
18 |
19 | try:
20 | MODULE = os.path.dirname(os.path.realpath(__file__))
21 | except:
22 | MODULE = ""
23 |
24 | sys.path.insert(0, os.path.join(MODULE, "..", "..", "..", ".."))
25 |
26 | from _pattern.compat import text_type, string_types, basestring, imap, unicode
27 |
28 | # Import parser base classes.
29 | from _pattern.text import (
30 | Lexicon, Model, Morphology, Context, Parser as _Parser, ngrams, pprint, commandline,
31 | PUNCTUATION
32 | )
33 | # Import parser universal tagset.
34 | from _pattern.text import (
35 | penntreebank2universal,
36 | PTB, PENN, UNIVERSAL,
37 | NOUN, VERB, ADJ, ADV, PRON, DET, PREP, ADP, NUM, CONJ, INTJ, PRT, PUNC, X
38 | )
39 | # Import parse tree base classes.
40 | from _pattern.text.tree import (
41 | Tree, Text, Sentence, Slice, Chunk, PNPChunk, Chink, Word, table,
42 | SLASH, WORD, POS, CHUNK, PNP, REL, ANCHOR, LEMMA, AND, OR
43 | )
44 | # Import sentiment analysis base classes.
45 | from _pattern.text import (
46 | Sentiment, NOUN, VERB, ADJECTIVE, ADVERB
47 | )
48 | # Import verb tenses.
49 | from _pattern.text import (
50 | INFINITIVE, PRESENT, PAST, FUTURE,
51 | FIRST, SECOND, THIRD,
52 | SINGULAR, PLURAL, SG, PL,
53 | INDICATIVE, IMPERATIVE, SUBJUNCTIVE,
54 | PROGRESSIVE,
55 | PARTICIPLE, GERUND
56 | )
57 | # Import inflection functions.
58 | from _pattern.text.de.inflect import (
59 | article, referenced, DEFINITE, INDEFINITE,
60 | pluralize, singularize, NOUN, VERB, ADJECTIVE,
61 | grade, comparative, superlative, COMPARATIVE, SUPERLATIVE,
62 | verbs, conjugate, lemma, lexeme, tenses,
63 | predicative, attributive,
64 | gender, MASCULINE, MALE, FEMININE, FEMALE, NEUTER, NEUTRAL, PLURAL, M, F, N, PL,
65 | NOMINATIVE, ACCUSATIVE, DATIVE, GENITIVE, SUBJECT, OBJECT, INDIRECT, PROPERTY
66 | )
67 | # Import all submodules.
68 | from _pattern.text.de import inflect
69 |
70 | sys.path.pop(0)
71 |
72 | #--- GERMAN PARSER ---------------------------------------------------------------------------------
73 | # The German parser (accuracy 96% for known words) is based on Schneider & Volk's language model:
74 | # Schneider, G. & Volk, M. (1998).
75 | # Adding Manual Constraints and Lexical Look-up to a Brill-Tagger for German.
76 | # Proceedings of the ESSLLI workshop on recent advances in corpus annotation. Saarbrucken, Germany.
77 | # http://www.zora.uzh.ch/28579/
78 |
79 | # The lexicon uses the Stuttgart/Tubinger Tagset (STTS):
80 | # https://files.ifi.uzh.ch/cl/tagger/UIS-STTS-Diffs.html
81 | STTS = "stts"
82 | stts = tagset = {
83 | "ADJ": "JJ",
84 | "ADJA": "JJ", # das große Haus
85 | "ADJD": "JJ", # er ist schnell
86 | "ADV": "RB", # schon
87 | "APPR": "IN", # in der Stadt
88 | "APPRART": "IN", # im Haus
89 | "APPO": "IN", # der Sache wegen
90 | "APZR": "IN", # von jetzt an
91 | "ART": "DT", # der, die, eine
92 | "ARTDEF": "DT", # der, die
93 | "ARTIND": "DT", # eine
94 | "CARD": "CD", # zwei
95 | "CARDNUM": "CD", # 3
96 | "KOUI": "IN", # [um] zu leben
97 | "KOUS": "IN", # weil, damit, ob
98 | "KON": "CC", # und, oder, aber
99 | "KOKOM": "IN", # als, wie
100 | "KONS": "IN", # usw.
101 | "NN": "NN", # Tisch, Herr
102 | "NNS": "NNS", # Tischen, Herren
103 | "NE": "NNP", # Hans, Hamburg
104 | "PDS": "DT", # dieser, jener
105 | "PDAT": "DT", # jener Mensch
106 | "PIS": "DT", # keiner, viele, niemand
107 | "PIAT": "DT", # kein Mensch
108 | "PIDAT": "DT", # die beiden Brüder
109 | "PPER": "PRP", # ich, er, ihm, mich, dir
110 | "PPOS": "PRP$", # meins, deiner
111 | "PPOSAT": "PRP$", # mein Buch, deine Mutter
112 | "PRELS": "WDT", # der Hund, [der] bellt
113 | "PRELAT": "WDT", # der Mann, [dessen] Hund bellt
114 | "PRF": "PRP", # erinnere [dich]
115 | "PWS": "WP", # wer
116 | "PWAT": "WP", # wessen, welche
117 | "PWAV": "WRB", # warum, wo, wann
118 | "PAV": "RB", # dafur, dabei, deswegen, trotzdem
119 | "PTKZU": "TO", # zu gehen, zu sein
120 | "PTKNEG": "RB", # nicht
121 | "PTKVZ": "RP", # pass [auf]!
122 | "PTKANT": "UH", # ja, nein, danke, bitte
123 | "PTKA": "RB", # am schönsten, zu schnell
124 | "VVFIN": "VB", # du [gehst], wir [kommen] an
125 | "VAFIN": "VB", # du [bist], wir [werden]
126 | "VVINF": "VB", # gehen, ankommen
127 | "VAINF": "VB", # werden, sein
128 | "VVIZU": "VB", # anzukommen
129 | "VVIMP": "VB", # [komm]!
130 | "VAIMP": "VB", # [sei] ruhig!
131 | "VVPP": "VBN", # gegangen, angekommen
132 | "VAPP": "VBN", # gewesen
133 | "VMFIN": "MD", # dürfen
134 | "VMINF": "MD", # wollen
135 | "VMPP": "MD", # gekonnt
136 | "SGML": "SYM", #
137 | "FM": "FW", #
138 | "ITJ": "UH", # ach, tja
139 | "XY": "NN", #
140 | "XX": "NN", #
141 | "LINUM": "LS", # 1.
142 | "C": ",", # ,
143 | "Co": ":", # :
144 | "Ex": ".", # !
145 | "Pc": ")", # )
146 | "Po": "(", # (
147 | "Q": ".", # ?
148 | "QMc": "\"", # "
149 | "QMo": "\"", # "
150 | "S": ".", # .
151 | "Se": ":", # ;
152 | }
153 |
154 | def stts2penntreebank(token, tag):
155 | """ Converts an STTS tag to a Penn Treebank II tag.
156 | For example: ohne/APPR => ohne/IN
157 | """
158 | return (token, stts.get(tag, tag))
159 |
160 | def stts2universal(token, tag):
161 | """ Converts an STTS tag to a universal tag.
162 | For example: ohne/APPR => ohne/PREP
163 | """
164 | if tag in ("KON", "KOUI", "KOUS", "KOKOM"):
165 | return (token, CONJ)
166 | if tag in ("PTKZU", "PTKNEG", "PTKVZ", "PTKANT"):
167 | return (token, PRT)
168 | if tag in ("PDF", "PDAT", "PIS", "PIAT", "PIDAT", "PPER", "PPOS", "PPOSAT"):
169 | return (token, PRON)
170 | if tag in ("PRELS", "PRELAT", "PRF", "PWS", "PWAT", "PWAV", "PAV"):
171 | return (token, PRON)
172 | return penntreebank2universal(*stts2penntreebank(token, tag))
173 |
174 | #let's add some legal abbreviations, too
175 | #let's also completely rule out at least simple ordinals
176 | #let's also rule out anything that could be a date
177 | ABBREVIATIONS = set((
178 | "Abs.", "Abt.", "Ass.", "Br.", "Ch.", "Chr.", "Cie.", "Co.", "Dept.", "Diff.",
179 | "Dr.", "Eidg.", "Exp.", "Fam.", "Fr.", "Hrsg.", "Inc.", "Inv.", "Jh.", "Jt.", "Kt.",
180 | "Mio.", "Mrd.", "Mt.", "Mte.", "Nr.", "Nrn.", "Ord.", "Ph.", "Phil.", "Pkt.",
181 | "Prof.", "Pt.", " S.", "St.", "Stv.", "Tit.", "VII.", "al.", "begr.","bzw.",
182 | "chem.", "dent.", "dipl.", "e.g.", "ehem.", "etc.", "excl.", "exkl.", "gem.", "hum.",
183 | "i.e.", "incl.", "ing.", "inkl.", "int.", "iur.", "lic.", "med.", "no.", "oec.",
184 | "phil.", "phys.", "pp.", "psych.", "publ.", "rer.", "sc.", "soz.", "spez.", "stud.",
185 | "theol.", "usw.", "v.", "vet.", "vgl.", "vol.", "wiss.",
186 | "d.h.", "h.c.", u"o.ä.", "u.a.", "z.B.", "z.T.", "z.Zt.", "z. B.", "d. h.", "h. c.",
187 | u"o. ä.", "u. a.", "z. B.", "z. T.", "z. Zt.",
188 | "BGBl.", "ABl.", "Bundesgesetzbl.",
189 | "0.", "1.", "2.", "3.", "4.", "5.", "6.", "7.", "8.", "9.", "10.", "11.", "12.", "13.",
190 | "14.", "15.", "16.", "17.", "18.", "19.", "20.", "21.", "22.", "23.", "24.", "25.", "26.",
191 | "27.", "28.", "29.", "30.", "31."
192 |
193 | ))
194 |
195 | def find_lemmata(tokens):
196 | """ Annotates the tokens with lemmata for plural nouns and conjugated verbs,
197 | where each token is a [word, part-of-speech] list.
198 | """
199 | for token in tokens:
200 | word, pos, lemma = token[0], token[1], token[0]
201 | if pos.startswith(("DT", "JJ")):
202 | lemma = predicative(word)
203 | if pos == "NNS":
204 | lemma = singularize(word)
205 | if pos.startswith(("VB", "MD")):
206 | lemma = conjugate(word, INFINITIVE) or word
207 | token.append(lemma.lower())
208 | return tokens
209 |
210 | class Parser(_Parser):
211 |
212 | def find_tokens(self, tokens, **kwargs):
213 | kwargs.setdefault("abbreviations", ABBREVIATIONS)
214 | kwargs.setdefault("replace", {})
215 | return _Parser.find_tokens(self, tokens, **kwargs)
216 |
217 | def find_lemmata(self, tokens, **kwargs):
218 | return find_lemmata(tokens)
219 |
220 | def find_tags(self, tokens, **kwargs):
221 | if kwargs.get("tagset") in (PENN, None):
222 | kwargs.setdefault("map", lambda token, tag: stts2penntreebank(token, tag))
223 | if kwargs.get("tagset") == UNIVERSAL:
224 | kwargs.setdefault("map", lambda token, tag: stts2universal(token, tag))
225 | if kwargs.get("tagset") is STTS:
226 | kwargs.setdefault("map", lambda token,tag: (token, tag))
227 | # The lexicon uses Swiss spelling: "ss" instead of "ß".
228 | # We restore the "ß" after parsing.
229 | tokens_ss = [t.replace(u"ß", "ss") for t in tokens]
230 | tokens_ss = _Parser.find_tags(self, tokens_ss, **kwargs)
231 | return [[w] + tokens_ss[i][1:] for i, w in enumerate(tokens)]
232 |
233 | parser = Parser(
234 | lexicon = os.path.join(MODULE, "de-lexicon.txt"),
235 | frequency = os.path.join(MODULE, "de-frequency.txt"),
236 | morphology = os.path.join(MODULE, "de-morphology.txt"),
237 | context = os.path.join(MODULE, "de-context.txt"),
238 | default = ("NN", "NE", "CARDNUM"),
239 | language = "de"
240 | )
241 |
242 | lexicon = parser.lexicon # Expose lexicon.
243 |
244 | def tokenize(s, *args, **kwargs):
245 | """ Returns a list of sentences, where punctuation marks have been split from words.
246 | """
247 | return parser.find_tokens(s, *args, **kwargs)
248 |
249 | def parse(s, *args, **kwargs):
250 | """ Returns a tagged Unicode string.
251 | """
252 | return parser.parse(s, *args, **kwargs)
253 |
254 | def parsetree(s, *args, **kwargs):
255 | """ Returns a parsed Text from the given string.
256 | """
257 | return Text(parse(s, *args, **kwargs))
258 |
259 | def tree(s, token=[WORD, POS, CHUNK, PNP, REL, LEMMA]):
260 | """ Returns a parsed Text from the given parsed string.
261 | """
262 | return Text(s, token)
263 |
264 | def tag(s, tokenize=True, encoding="utf-8", **kwargs):
265 | """ Returns a list of (token, tag)-tuples from the given string.
266 | """
267 | tags = []
268 | for sentence in parse(s, tokenize, True, False, False, False, encoding, **kwargs).split():
269 | for token in sentence:
270 | tags.append((token[0], token[1]))
271 | return tags
272 |
273 | def keywords(s, top=10, **kwargs):
274 | """ Returns a sorted list of keywords in the given string.
275 | """
276 | return parser.find_keywords(s, top=top, frequency=parser.frequency)
277 |
278 | split = tree # Backwards compatibility.
279 |
280 | #---------------------------------------------------------------------------------------------------
281 | # python -m pattern.de xml -s "Ein Unglück kommt selten allein." -OTCL
282 |
283 | if __name__ == "__main__":
284 | commandline(parse)
285 |
--------------------------------------------------------------------------------
160 | {%- block content %}
161 | {% if theme_style_external_links|tobool %}
162 |
187 | {% include "versions.html" %}
188 |
189 | {% if not embedded %}
190 |
191 | {# XXX Sphinx 1.8.0 made this an external js-file, quick fix until we refactor the template to inherert more blocks directly from sphinx #}
192 | {% if sphinx_version >= "1.8.0" %}
193 |
194 | {%- for scriptfile in script_files %}
195 | {{ js_tag(scriptfile) }}
196 | {%- endfor %}
197 | {% else %}
198 |
209 | {%- for scriptfile in script_files %}
210 |
211 | {%- endfor %}
212 | {% endif %}
213 |
214 | {% endif %}
215 |
216 |
217 |
218 |
223 |
224 | {%- block footer %} {% endblock %}
225 |
226 |
227 |
228 |
--------------------------------------------------------------------------------
/README.rst:
--------------------------------------------------------------------------------
1 | ==================
2 | textblob-de README
3 | ==================
4 |
5 |
6 | .. image:: https://img.shields.io/pypi/v/textblob-de.svg
7 | :target: https://pypi.python.org/pypi/textblob-de/
8 | :alt: textblob_de - latest PyPI version
9 |
10 | .. image:: https://travis-ci.org/markuskiller/textblob-de.png?branch=dev
11 | :target: https://travis-ci.org/markuskiller/textblob-de
12 | :alt: Travis-CI
13 |
14 | .. image:: https://readthedocs.org/projects/textblob-de/badge/?version=latest
15 | :target: http://textblob-de.readthedocs.org/en/latest/
16 | :alt: Documentation Status
17 |
18 | .. image:: https://img.shields.io/pypi/dm/textblob-de.svg
19 | :target: https://pypi.python.org/pypi/textblob-de/
20 | :alt: Number of PyPI downloads
21 |
22 | .. image:: https://img.shields.io/github/license/markuskiller/textblob-de.svg
23 | :target: http://choosealicense.com/licenses/mit/
24 | :alt: LICENSE info
25 |
26 | German language support for `TextBlob
163 | {% else %}
164 |
183 |
184 |
185 |
186 |
165 | {% endif %}
166 | {% include "breadcrumbs.html" %}
167 |
181 | {%- endblock %}
182 |
168 | {%- block document %}
169 |
178 | {%- endblock %}
179 | {% include "footer.html" %}
180 |