This tool will help you quickly analyze a narrative.
12 |
By looking at the structure of the text, and the main actors in the text, this tool can help you gain insight in the dialog structure..blah blah enzo :)
13 |
14 |
19 |
20 |
21 |
22 |
--------------------------------------------------------------------------------
/run-tests.sh:
--------------------------------------------------------------------------------
1 | #!/usr/bin/env bash
2 |
3 | #
4 | # File: run-tests.sh
5 | #
6 | # This file is part of the Narralyzer package.
7 | # see: http://lab.kb.nl/tool/narralyzer
8 |
9 | # Little wrapper to datestamp outgoing messages.
10 | function inform_user() {
11 | msg="$1"
12 | timestamp=`date "+%Y-%m-%d %H:%M"`
13 | echo "$timestamp: Narralyzer start_stanford.sh $msg"
14 | }
15 |
16 | function run_test() {
17 | fname="$1"
18 | inform_user "Running doctests for: $fname"
19 | python2.7 "$fname" test || exit -1
20 | }
21 |
22 |
23 | (
24 | inform_user "Starting Stanford."
25 | . start_stanford.sh waitforstartup
26 |
27 | inform_user "Crawling into virtualenv."
28 | . env/bin/activate
29 |
30 | run_test "./narralyzer/stanford_ner_wrapper.py"
31 | run_test "./narralyzer/lang_lib.py"
32 | run_test "./narralyzer/utils.py"
33 | ) || exit -1
34 |
--------------------------------------------------------------------------------
/docs/source/narralyzer.rst:
--------------------------------------------------------------------------------
1 | narralyzer package
2 | ==================
3 |
4 | Submodules
5 | ----------
6 |
7 | narralyzer.lang_lib module
8 | --------------------------
9 |
10 | .. automodule:: narralyzer.lang_lib
11 | :members:
12 | :undoc-members:
13 | :show-inheritance:
14 |
15 | narralyzer.stanford_ner_wrapper module
16 | --------------------------------------
17 |
18 | .. automodule:: narralyzer.stanford_ner_wrapper
19 | :members:
20 | :undoc-members:
21 | :show-inheritance:
22 |
23 | narralyzer.visualize_ners module
24 | --------------------------------
25 |
26 | .. automodule:: narralyzer.visualize_ners
27 | :members:
28 | :undoc-members:
29 | :show-inheritance:
30 |
31 |
32 | Module contents
33 | ---------------
34 |
35 | .. automodule:: narralyzer
36 | :members:
37 | :undoc-members:
38 | :show-inheritance:
39 |
--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
1 | Narralyzer will help you quickly analyze the occurrence of and relations between Entities in narrative texts, such as novels, short stories and newspaper articles in four languages. The following aspects of narrative texts are included in the analysis:
2 |
3 | - NER (Named Entity Recognition)
4 | - Relations between Entities
5 | - Entity-text extraction (aura of n = 5)
6 |
7 |
8 | 
9 |
10 | The backend library also does POS tagging and sentiment analysis, however this is not exposed in the frontend.
11 |
12 | - Info: http://lab.kb.nl/tool/narralyzer
13 | - Demo: https://kbresearch.nl/narralyzer/
14 | - Language models:
15 | - https://github.com/WillemJan/Narralyzer_languagemodel
16 | - https://github.com/WillemJan/Narralyzer_Dutch_languagemodel
17 |
--------------------------------------------------------------------------------
/site/templates/index.html:
--------------------------------------------------------------------------------
1 | {% extends "main.html" %}
2 | {% block body %}
3 |
4 |
This tool will help you quickly analyze a narrative.
5 |
By looking at the structure of the text, and the main actors in the text, this tool can help you gain insight in the dialog structure..blah blah enzo :)
6 |
Please note the following guidlines for optimal usage of this tool:
7 |
8 |
Chapters in the text should be classified as such.
9 |
Text must be either in Dutch or English (Due to available NER-engines).
10 |
11 | (Wellicht moet er eerst een intro pagina voordat we meteen beginnen met uploaden..)
12 |
16 |
17 | {% endblock %}
18 |
--------------------------------------------------------------------------------
/conf/config.ini:
--------------------------------------------------------------------------------
1 | [main]
2 | stanford_ner_path="language_models/stanford/ner"
3 | stanford_core="http://nlp.stanford.edu/software/stanford-corenlp-full-2015-12-09.zip"
4 | tika="http://apache.cs.uu.nl/tika/tika-app-1.13.jar"
5 |
6 | [lang_de]
7 | port = 9990
8 | stanford_ner="german.dewac_175m_600.crf.ser.gz"
9 | stanford_ner_source="http://nlp.stanford.edu/software/stanford-german-2016-01-19-models.jar"
10 |
11 | [lang_en]
12 | port = 9991
13 | stanford_ner="english.all.3class.distsim.crf.ser.gz"
14 | stanford_ner_source="http://nlp.stanford.edu/software/stanford-english-corenlp-2016-01-10-models.jar"
15 |
16 | [lang_nl]
17 | port = 9992
18 | stanford_ner="dutch.crf.gz"
19 | stanford_ner_source="https://raw.githubusercontent.com/WillemJan/Narralyzer_Dutch_languagemodel/master/dutch.crf.gz"
20 |
21 | [lang_sp]
22 | port = 9993
23 | stanford_ner="spanish.ancora.distsim.s512.crf.ser.gz"
24 | stanford_ner_source="http://nlp.stanford.edu/software/stanford-spanish-corenlp-2015-10-14-models.jar"
25 |
--------------------------------------------------------------------------------
/site/static/css/style.css:
--------------------------------------------------------------------------------
1 | * {
2 | margin: 0px 0px 0px 0px;
3 | padding: 0px 0px 0px 0px;
4 | }
5 |
6 | body {
7 | background-color: #FFF;
8 | color: #000;
9 | font-family: Arial,Helvetica,sans-serif,Verdana;
10 | font-size: small;
11 | }
12 |
13 | #uploadform {
14 | border: 1px solid #000;
15 | padding: 20px;
16 | width: 300px;
17 | }
18 |
19 | .chapter {
20 | border: 1px solid #000;
21 | margin: 10px;
22 | height: 200px;
23 | overflow: auto;
24 | padding: 5px;
25 | width: 70%;
26 | }
27 |
28 | h1 {
29 | text-align: left;
30 | margin-left: 40%;
31 | padding-top: 30px;
32 | font-family: 'Source Sans Pro', sans-serif;
33 | font-size: 40px;
34 | }
35 |
36 | h2 {
37 | text-align: left;
38 | margin-left: 35%;
39 | font-family: 'Source Sans Pro', sans-serif;
40 | font-size: 20px;
41 | font-style: italic;
42 | }
43 |
44 |
45 | hr {
46 | color: lightblue;
47 | float: left;
48 | width: 40%;
49 | }
50 |
51 | .header {
52 | background: #CACFCA;
53 | height: 120px;
54 | }
55 |
56 | .chapter_selected p {
57 | background-color: #328832;
58 | margin-top: 20px;
59 | margin-left: 100px;
60 | overflow: auto;
61 | height: 100px;
62 | width: 800px;
63 | }
64 |
65 | #header_logo_ru {
66 | padding-top: 5px;
67 | float: right;
68 | clear: both;
69 | width: 200px;
70 | }
71 |
72 | #header_logo_kb {
73 | padding-top: 20px;
74 | float: right;
75 | width: 200px;
76 | }
77 |
78 | input[type="radio"] {
79 | margin-left: 15px;
80 | }
81 |
--------------------------------------------------------------------------------
/site/.htaccess:
--------------------------------------------------------------------------------
1 |
2 | SetHandler wsgi-script
3 | Options +ExecCGI
4 |
5 |
6 | RewriteEngine on
7 | RewriteBase /
8 | RewriteCond %{REQUEST_URI} !^/robots.txt
9 | RewriteCond %{REQUEST_URI} !^/static
10 | RewriteCond %{REQUEST_URI} !^(/.*)+index.py
11 | RewriteRule ^(.*)$ index.py/$1 [PT]
12 |
--------------------------------------------------------------------------------
/README.txt:
--------------------------------------------------------------------------------
1 | Welcome to Narralyzer.
2 | Travis-CI status
3 | *Warning this site & code is work in progress*
4 | Intermediate result of parser backendlog.pdf
5 | Intermediate result of character visualization 1, 2, still needs some work :)
6 | What does Narralyzer do?
7 |
8 | Narralyzer will help you quickly analyze the occurrence of and relations between Entities in narrative texts, such as novels, short stories and newspaper articles in four languages. The following aspects of narrative texts are included in the analysis:
9 |
10 | NER (Named Entity Recognition)
11 | Relations between Entities
12 | Entity-text detection (aura of n = x)
13 |
14 | Based on the NER and relation-analysis:
15 |
16 | A visualization (using GraphViz, see www.graphviz.org) of the relations between Entities can be created, per text-part and for the entire text
17 |
18 | Entity-text, per text-part and for the entire text, can be downloaded, so the user can then use it as material for performing more computational analyzes
19 |
20 | What does Narralyzer need from you?
21 |
22 | In order for Narralyzer to run properly, the input text should meet the following requirements:
23 | Texts should be in either:Dutch, English, German or Spanish (Due to available NER-models)
24 | Texts should be in one of the following formats:
25 |
26 | TEI
27 | PDF
28 | Epub
29 | Plain text
30 |
31 | Text-parts (i.e. chapters or other relevant structural text-parts) should be classified as such;
32 | Narralyzer will explicitly ask you to do this.
33 |
34 | Exception: when the text-format is PDF or Epub and provides metadata on text partitions, manual text cutting is not always needed.
35 |
36 | Note: for optimal usage of Narralyzer manual partitioning is, for now, the most reliable option.
37 |
38 | How to cite using Narralyzer
39 |
40 | If you use Narralyzer for your research, educational purposes or in any other way, please cite as follows: Wildschut, P.A., Faber, W-J. (2016) Narralyzer. Analyzing Narratives with DH-tools. [http://www.narralyzer.com/] Hosted by the National Library of the Netherlands (KB) & Radboud University Nijmegen.
41 | Contact
42 |
43 | For questions and remarks, please contact Puck Wildschut (p.wildschut@let.ru.nl) For technical support, contact Willem-Jan Faber ([willemjan.faber@kb.nl]) Further information
44 |
45 | Narralyzer has been created within the context of the Researcher-in-residence programme, funded by the National Library of the Netherlands (KB). Narralyzer is the intellectual property of its authors (sic) and the Radboud University Nijmegen.
46 |
47 |
--------------------------------------------------------------------------------
/site/templates/file_uploaded.html:
--------------------------------------------------------------------------------
1 |
2 |
3 |
4 | Narralyzer-1
5 |
6 |
7 |
8 |
9 |
10 |
11 |
17 | Recieved file is of type: {{ ftype }}
18 | Original filesize (absolute): {{ filesize }}
19 |
20 |
21 |
Nr of ascii characters [a-zA-Z0-9] : {{ t_ascii_letters }}
22 |
Nr of punctuation characters [!"#$%&\'()*+,-./:;<=>?@[\\]^_`{|}~] :{{ t_punct_letters }}
23 |
Nr of noise char [everything not above] : {{ t_noise_letters }}
24 |
25 |
26 |
27 |
28 |
29 | The following information was dectected automaticly, this is your last change to change it before we start the final analysis.
30 | (of cource you can re-upload and see what happens if you play arround with the structure of the chapters.)
31 |
32 |
67 |
68 |
69 |
70 |
71 |
72 |
--------------------------------------------------------------------------------
/narralyzer/utils.py:
--------------------------------------------------------------------------------
1 | #!/usr/bin/env python2.7
2 | # -*- coding: utf-8 -*-
3 | """
4 | narralyzer.utils
5 | ~~~~~~~~~~~~~~~~
6 | Misc utilities to support Narralyzer.
7 |
8 | :copyright: (c) 2016 Koninklijke Bibliotheek, by Willem-Jan Faber.
9 | :license: GPLv3, see licence.txt for more details.
10 | """
11 |
12 | import sys
13 | reload(sys)
14 | sys.setdefaultencoding('utf-8')
15 |
16 | import codecs
17 | import cPickle
18 | import gzip
19 | import json
20 | import logging
21 | import os
22 | import time
23 |
24 |
25 | # Define how often you want to see messages
26 | DEFAULT_LOGLEVEL = logging.DEBUG
27 |
28 | # Define how pretty the logs look
29 | LOG_FORMAT = '%(asctime)s %(name)-12s %(levelname)-8s %(message)s'
30 |
31 | # Get the package-base-path
32 | BASE_PATH = ''
33 |
34 | # Path to test data
35 | TESTDATA_PATH = os.sep +'test_data' + os.sep
36 |
37 | # Path to output files
38 | OUTPUT_PATH = os.sep + 'out' + os.sep
39 |
40 | def logger(name, loglevel='warning'):
41 | try:
42 | loglevel = getattr(logging,
43 | [l for l in dir(logging) if (
44 | l.isupper() and l.lower()) == loglevel].pop())
45 | except:
46 | loglevel = DEFAULT_LOGLEVEL
47 |
48 | logger = logging.getLogger(name)
49 | handler = logging.StreamHandler()
50 | formatter = logging.Formatter(LOG_FORMAT)
51 | handler.setFormatter(formatter)
52 | logger.addHandler(handler)
53 | logger.setLevel(loglevel)
54 | return logger
55 |
56 | def narralyze(input_text, output_name=False, return_json=True, verbose=True):
57 | from lang_lib import Language
58 |
59 | if not input_text:
60 | msg = "Did not recieve any text to work with"
61 | return
62 |
63 | output_name = os.path.join(
64 | BASE_PATH,
65 | OUTPUT_PATH,
66 | output_name)
67 |
68 | '''
69 |
70 | if not os.path.isfile(output_name):
71 | # Open and read the test-book.
72 | fh = codecs.open(fname_txt, 'r', encoding='utf-8')
73 | book = fh.read().replace('\n', ' ')
74 | fh.close()
75 |
76 | # Tag each sentence.
77 | t = time.time()
78 | lang = Language(book)
79 | lang.parse()
80 | if verbose:
81 | print("Took %s to parse %s bytes" % (str(round(time.time() - t)),
82 | str(len(book))))
83 |
84 | # Store the result to a compressed pickle file.
85 | fh = gzip.GzipFile(ofname, 'wb')
86 | fh.write(cPickle.dumps(lang.result))
87 | fh.close()
88 | result = lang.result
89 | else:
90 | if not os.path.isfile(ofname):
91 | ofname = os.path.join("..", OUTPUT, fname.replace('.txt', '.pickle.gz'))
92 | # Load the tagged sentences from a compressed pickle file.
93 | fh = gzip.GzipFile(ofname, 'rb')
94 | raw_data = ""
95 | data = fh.read()
96 |
97 | while data:
98 | raw_data += data
99 | data = fh.read()
100 |
101 | langlib_result = cPickle.loads(raw_data)
102 | fh.close()
103 | result = langlib_result
104 |
105 | if return_json:
106 | return json.dumps(result)
107 | return result
108 | '''
109 |
110 | if __name__ == "__main__":
111 | print("Relativity theory")
112 | #if len(sys.argv) >= 2 and 'test' in " ".join(sys.argv):
113 | # import doctest
114 | # doctest.testmod(verbose=True)
115 |
116 | #from pprint import pprint
117 | #book = load_test_book('dutch_book_gbid_20060.txt')
118 | #pprint(book)
119 |
--------------------------------------------------------------------------------
/narralyzer/visualize_ners.py:
--------------------------------------------------------------------------------
1 | #!/usr/bin/env python2.7
2 | # -*- coding: utf-8 -*-
3 | """
4 | narralyzer.visualize_ners
5 | ~~~~~~~~~~~~~~~~~~~~~~~~~
6 | Implements a dialog visualisation between person's extracted from text.
7 |
8 | :copyright: (c) 2016 Koninklijke Bibliotheek, by Willem Jan Faber.
9 | :license: GPLv3, see licence.txt for more details.
10 | """
11 |
12 | import sys
13 | reload(sys)
14 | sys.setdefaultencoding('utf-8')
15 |
16 | import os
17 | import string
18 | import sys
19 |
20 | from django.utils.encoding import smart_text
21 | from graphviz import Digraph
22 | from pprint import pprint
23 |
24 |
25 | def analyze(ner_array, dot, name):
26 | ner = {}
27 | print("Total nr of NER's: %i " % len(ner_array))
28 | for item in ner_array:
29 | if not item in ner:
30 | ner[item] = 0
31 | else:
32 | ner[item] += 1
33 |
34 | ranks = sorted(ner.items(), key=lambda x: x[1])
35 | to_remove = []
36 |
37 | '''
38 | for item in ranks:
39 | if item[1] < 1:
40 | to_remove.append(item[0])
41 | '''
42 |
43 | for item in to_remove:
44 | ner.pop(item)
45 |
46 | person_matrix = {}
47 |
48 | interaction_scale = 0
49 |
50 | prev_item = ner_array[-1]
51 | for item in ner:
52 | person = item
53 | person_matrix[person] = {}
54 | for item in ner_array:
55 | if not item == person and prev_item == person:
56 | if not item in person_matrix[person]:
57 | person_matrix[person][item] = 1
58 | else:
59 | person_matrix[person][item] += 1
60 | if person_matrix[person][item] > interaction_scale:
61 | interaction_scale = person_matrix[person][item]
62 | prev_item = item
63 |
64 | print("SCALE:", interaction_scale)
65 | pprint(person_matrix)
66 |
67 | translate_table = {}
68 |
69 | i = 0
70 | for item in person_matrix:
71 | translate_table[item] = string.letters[i]
72 | dot.node(string.letters[i], item)
73 | print(item, string.letters[i])
74 | i += 1
75 |
76 | for item in person_matrix:
77 | for person in person_matrix[item]:
78 | if (person_matrix[item][person]):
79 | if item in translate_table and person in translate_table:
80 | print(person_matrix[item][person])
81 | #print(translate_table[item])
82 | #print(translate_table[person])
83 | dot.edge(translate_table[item], translate_table[person], color=color_code(person_matrix[item][person], interaction_scale), bgcolor='red', arrowtail='both', label=str(person_matrix[item][person]))
84 | #print(color_code(person_matrix[item][person], interaction_scale))
85 | #print([ translate_table[item] , translate_table[person] ])
86 | dot.render(name + "_graphviz_", view=False)
87 |
88 | def color_code(value, max_value):
89 | per = (value * (max_value / 100.0)) * 100
90 | print(per)
91 | if per < 25.0:
92 | return 'green'
93 | if per < 50.0:
94 | return 'blue'
95 | if per < 75.0:
96 | return 'yellow'
97 | return 'red'
98 |
99 | if __name__ == "__main__":
100 | name = 'vondel'
101 |
102 | dot = Digraph(comment=name)
103 | ner_array = []
104 | result = stanford_ner_wrapper(data, 9991)
105 |
106 | for ner in result.get('ners'):
107 | if ('per' or 'person') in ner.get('tag'):
108 | ner_array.append(ner.get('string'))
109 |
110 | pprint(ner_array)
111 | analyze(ner_array, dot, name)
112 |
--------------------------------------------------------------------------------
/narralyzer/config.py:
--------------------------------------------------------------------------------
1 | #!/usr/bin/env python2.7
2 | # -*- coding: utf-8 -*-
3 | '''
4 | narralyzer.config
5 | ~~~~~~~~~~~~~~~~~
6 |
7 | Handle misc config variables.
8 |
9 | :copyright: (c) 2016 Koninklijke Bibliotheek, by Willem-Jan Faber.
10 | :license: GPLv3, see licence.txt for more details.
11 | '''
12 |
13 | import sys
14 | reload(sys)
15 | sys.setdefaultencoding('utf-8')
16 |
17 | from os import path, environ, getenv
18 | from ConfigParser import ConfigParser
19 |
20 | try:
21 | from narralyzer.util import logger as logger
22 | except:
23 | from utils import logger
24 |
25 | class Config():
26 | """
27 | Configuration file dict.
28 |
29 | >>> config = Config()
30 | >>> config.get('supported_languages')
31 | 'DE EN NL SP'
32 | """
33 |
34 | config = {
35 | 'config_file': 'conf/config.ini',
36 | 'models': {},
37 | 'root': None,
38 | 'supported_languages': []
39 | }
40 |
41 |
42 | def __init__(self):
43 | if self.config.get('root', None) is None:
44 | root = path.join(path.dirname(path.abspath(__file__)))
45 | root = path.join(root, '..')
46 | self.config['root'] = path.abspath(root)
47 |
48 | root = self.config['root']
49 | logger("My basepath={0}".format(root))
50 | config_file = path.join(root, self.config.get('config_file'))
51 |
52 | if not path.isfile(config_file):
53 | print("Could not open config file: {0}".format(path.abspath(config_file)))
54 | sys.exit(-1)
55 |
56 | self.config['config_file'] = config_file
57 | config = ConfigParser()
58 | config.read(config_file)
59 |
60 | for section in config.sections():
61 | if section.startswith('lang_'):
62 | language = section.replace('lang_', '')
63 | port = config.get(section, 'port')
64 | stanford_ner = config.get(section, 'stanford_ner')
65 | self.config['models'][language] = {
66 | 'port': port,
67 | 'stanford_ner': stanford_ner}
68 | if section == 'main':
69 | stanford_ner_path = config.get(section, 'stanford_ner_path')
70 |
71 | for language in self.config.get('models'):
72 | if not language in self.config["supported_languages"]:
73 | self.config["supported_languages"].append(language)
74 |
75 | def get(self, variable):
76 | result = self.config.get(variable, None)
77 | if isinstance(result, list):
78 | return " ".join(sorted(result)).upper()
79 | return result
80 |
81 | def __repr__(self):
82 | current_config = "root: {0}\n" \
83 | "\tsupported_languages: {1}\n" \
84 | "\tconfig_file: {2}\n".format(
85 | self.config.get('root'),
86 | self.get('supported_languages'),
87 | self.config.get('config_file'))
88 | result = "Available config parameters:\n\t{0}\n\t{1}\n\nCurrent config:\n\t{2}".format(
89 | "- supported_languages",
90 | "- root",
91 | current_config.strip()
92 | )
93 | return result
94 |
95 | if __name__ == "__main__":
96 | config = Config()
97 | if len(sys.argv) >= 2 and not "test" in " ".join(sys.argv):
98 | result = config.get(sys.argv[1])
99 | if result is None:
100 | msg = "Config key {0} unknown."
101 | logger(msg)
102 | exit(-1)
103 | else:
104 | print(result)
105 | else:
106 | if len(sys.argv) >= 2 and "test" in " ".join(sys.argv):
107 | import doctest
108 | doctest.testmod(verbose=True)
109 | else:
110 | print(config)
111 |
--------------------------------------------------------------------------------
/start_stanford.sh:
--------------------------------------------------------------------------------
1 | #!/usr/bin/env bash
2 |
3 | #
4 | # File: start_stanford.sh
5 | #
6 | # This file is part of the Narralyzer package.
7 | # see: http://lab.kb.nl/tool/narralyzer
8 | #
9 |
10 | #
11 | # This program is free software: you can redistribute it and/or modify
12 | # it under the terms of the GNU General Public License as published by
13 | # the Free Software Foundation, either version 3 of the License, or
14 | # (at your option) any later version.
15 | #
16 | # This program is distributed in the hope that it will be useful,
17 | # but WITHOUT ANY WARRANTY; without even the implied warranty of
18 | # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
19 | # GNU General Public License for more details.
20 | #
21 | # You should have received a copy of the GNU General Public License
22 | # along with this program. If not, see .
23 | #
24 |
25 | DE_CLASSIFIER="../models/edu/stanford/nlp/models/ner/german.dewac_175m_600.crf.ser.gz"
26 | DE_PORT=9990
27 |
28 | EN_CLASSIFIER="../models/edu/stanford/nlp/models/ner/english.all.3class.distsim.crf.ser.gz"
29 | EN_PORT=9991
30 |
31 | # FR_CLASSIFIER="../models/edu/stanford/nlp/models/srparser/frenchSR.beam.ser.gz"
32 | # FR_PORT=9992
33 |
34 | NL_CLASSIFIER="../models/dutch.crf.gz"
35 | NL_PORT=9993
36 |
37 | SP_CLASSIFIER="../models//edu/stanford/nlp/models/ner/spanish.ancora.distsim.s512.crf.ser.gz"
38 | SP_PORT=9994
39 |
40 | SUPPORTED_LANG=$(narralyzer/config.py supported_languages)
41 |
42 | # Little wrapper to datestamp outgoing messages.
43 | function inform_user() {
44 | msg="$1"
45 | timestamp=`date "+%Y-%m-%d %H:%M"`
46 | echo "$timestamp: Narralyzer start_stanford.sh $msg"
47 | }
48 |
49 | # Path to Stanford-core lib.
50 | # (Should be installed the by install.sh).
51 | PATH_TO_STANFORD_CORE="stanford/core/"
52 | inform_user "Changing directory to $PATH_TO_STANFORD_CORE"
53 | cd $PATH_TO_STANFORD_CORE
54 |
55 | # Prefix for logfile output name, to turn logging off
56 | # change LOG to "/dev/null".
57 | LOG="stanford_"
58 |
59 | # Use system wide default java.
60 | JAVA=`which java`
61 | # Except if your hostname "fe2"
62 | # So this private litte hack is to be ignored.
63 | if [ $HOSTNAME == "fe2" ]; then
64 | JAVA=/home/aloha/java/bin/java
65 | fi
66 |
67 | java_version=($JAVA -version)
68 | inform_user "Using java version: $java_version"
69 |
70 | # Use a whopping 4g per language.
71 | JAVA_MEM="-mx4g"
72 |
73 | # From the Stanford repo:
74 | OS=`uname`
75 | # Some machines (older OS X, BSD, Windows environments) don't support readlink -e
76 | if hash readlink 2>/dev/null; then
77 | scriptdir=`dirname $0`
78 | else
79 | scriptpath=$(readlink -e "$0") || scriptpath=$0
80 | scriptdir=$(dirname "$scriptpath")
81 | fi
82 |
83 | # Fire several stanford core server.
84 | for lang in $(echo $SUPPORTED_LANG | sort | xargs);do
85 | classifier=$(eval "echo \$${lang}_CLASSIFIER")
86 | port=$(eval "echo \$${lang}_PORT")
87 | is_running=$(ps x | grep "$classifier" | grep -v 'grep' | wc -l)
88 | if [ "$is_running" == "1" ]; then
89 | inform_user "Not starting $lang on port $port for it is allready running."
90 | else
91 | inform_user "Starting Stanford-core for language: $lang on port: $port"
92 | inform_user "$JAVA $JAVA_MEM -Djava.net.preferIPv4Stack=true -cp $scriptdir/\* edu.stanford.nlp.ie.NERServer -port $port -loadClassifier $classifier -outputFormat inlineXML"
93 | # TODO Logging would be nice.
94 | $JAVA $JAVA_MEM -Djava.net.preferIPv4Stack=true -cp $scriptdir/\* edu.stanford.nlp.ie.NERServer -port $port -loadClassifier $classifier -outputFormat inlineXML > "$LOG$lang.log" 2>&1 &
95 | fi
96 | done
97 |
98 | # Wait until the cores are booted and responsive,
99 | # if parameter 'waitforstartup' is given to start_stanford.sh.
100 | for lang in $(echo $SUPPORTED_LANG | sort | xargs);do
101 | port=$(eval "echo \$${lang}_PORT")
102 | if [ "$1" == "waitforstartup" ];then
103 | count=$(lsof -i tcp -n | grep $port | wc -l)
104 | while [ "$count" != "1" ]; do
105 | inform_user "Waiting for Stanford-core: $lang port: $port"
106 | sleep 1
107 | count=$(lsof -i tcp -n | grep $port | wc -l)
108 | done
109 | fi
110 | done
111 |
112 | inform_user "Moving to directory where we started"
113 | cd -
114 |
--------------------------------------------------------------------------------
/install.sh:
--------------------------------------------------------------------------------
1 | #!/usr/bin/env bash
2 |
3 | #
4 | # File: install.sh
5 | #
6 | # This file is part of the Narralyzer package.
7 | # see: http://lab.kb.nl/tool/narralyzer
8 |
9 | # If you run into troubles try this:
10 | #
11 | # sudo apt-get install -y build-essesntials libdb-dev virtualenv python2.7 libxml2-dev libxslt1-dev
12 |
13 |
14 | # Tika will take care of most input document conversion.
15 | TIKA="http://apache.cs.uu.nl/tika/tika-app-1.13.jar"
16 |
17 | # Where Stanford core lives.
18 | STANFORD_CORE="http://nlp.stanford.edu/software/stanford-corenlp-full-2015-12-09.zip"
19 |
20 | # Where the language models live.
21 | STANFORD_DE="http://nlp.stanford.edu/software/stanford-german-2016-01-19-models.jar"
22 | STANFORD_EN="http://nlp.stanford.edu/software/stanford-english-corenlp-2016-01-10-models.jar"
23 | STANFORD_NL="https://raw.githubusercontent.com/WillemJan/Narralyzer_Dutch_languagemodel/master/dutch.crf.gz"
24 | STANFORD_SP="http://nlp.stanford.edu/software/stanford-spanish-corenlp-2015-10-14-models.jar"
25 |
26 | # Little wrapper to datestamp outgoing messages.
27 | function inform_user() {
28 | msg="$1"
29 | timestamp=`date "+%Y-%m-%d %H:%M"`
30 | echo "$timestamp: Narralyzer install.sh $msg"
31 | }
32 |
33 | # Fetch the given URL, and save to disk
34 | # use the 'basename' for storing.
35 | function get_if_not_there () {
36 | URL=$1
37 | if [ ! -f `basename $URL` ]; then
38 | inform_user "Fetching $URL..."
39 | wget_output=$(wget -q "$URL")
40 | if [ $? -ne 0 ]; then
41 | inform_user "Error while fetching $URL, time to exit."
42 | exit -1;
43 | fi
44 | else
45 | inform_user "Not fetching $URL, `basename \"$URL\"` allready there."
46 | fi
47 |
48 | }
49 |
50 | # Fetch and unpack the Stanford core package.
51 | function fetch_stanford_core {
52 | get_if_not_there $STANFORD_CORE
53 | if [ -f `basename $STANFORD_CORE` ]; then
54 | unzip -q -n `basename "$STANFORD_CORE"`
55 | rm `basename "$STANFORD_CORE"`
56 | ln -s `find -name \*full\* -type d` core
57 | fi
58 | }
59 |
60 | # Fetch and unpack the language models.
61 | # (Might move them into this repo for ease later).
62 | function fetch_stanford_lang_models {
63 | get_if_not_there $STANFORD_DE
64 | get_if_not_there $STANFORD_EN
65 | get_if_not_there $STANFORD_FR
66 | get_if_not_there $STANFORD_NL
67 | get_if_not_there $STANFORD_SP
68 | find . -name \*.jar -exec unzip -q -o '{}' ';'
69 | # rm *.jar <- Save some diskspace here.
70 | }
71 |
72 | # Check if Python2.7 is installed on the os,
73 | # we might need that in the near futute.
74 | is_python2_7_avail() {
75 | is_avail=$(which python2.7 | wc -l)
76 | if [ "$is_avail" = "0" ]; then
77 | inform_user "Python 2.7 is not available, helas. sudo apt-get install python2.7?"
78 | exit -1
79 | fi
80 | inform_user "Python 2.7 is available."
81 | }
82 |
83 | # Check if we find (Python) virtualenv.
84 | is_virtualenv_avail() {
85 | is_avail=$(which virtualenv | wc -l)
86 | if [ "$is_avail" = "0" ]; then
87 | inform_user "Virtualenv is not available, helas. sudo-apt-get install virtualenv?"
88 | exit -1
89 | fi
90 | inform_user "Virtualenv is available."
91 | }
92 |
93 | # Now move to install dir for installation of core and models.
94 | if [ ! -d 'stanford' ]; then
95 | mkdir stanford && cd stanford
96 | else
97 | cd stanford
98 | fi
99 |
100 | # If stanford-corenlp-full*.zip is allready there, do nothing.
101 | full=$(find -name \*full\* | wc -l)
102 | if [ "$full" = "0" ];then
103 | # Fetch stanford-core from their site,
104 | # and install it.
105 | fetch_stanford_core
106 | else
107 | inform_user "Not fetching stanford-core, allready there."
108 | fi
109 |
110 | # If the models are allready there, do nothing.
111 | if [ ! -d 'models' ]; then
112 | # Else fetch and unpack models.
113 | mkdir models && cd models
114 | fetch_stanford_lang_models
115 | cd ..
116 | fi
117 |
118 | # Now leave the install dir.
119 | cd ..
120 |
121 | # Check if the virtual env exists, if not, create one and within
122 | # the virtual env install the required packages.
123 | if [ ! -d "env" ]; then
124 | is_python2_7_avail
125 | is_virtualenv_avail
126 |
127 | inform_user "Creating new virtualenv using python2.7 in ./env"
128 | virtualenv -p python2.7 ./env
129 |
130 | inform_user "Entering virtualenv, to leave: deactivate"
131 | source env/bin/activate
132 |
133 | inform_user "Upgrade pip and setuptools to latest version."
134 | pip install --upgrade pip setuptools
135 |
136 | if [ -f ~/requirements.txt ]; then
137 | req="~/requirements.txt"
138 | else
139 | req=`find ~ -name 'requirements.txt' | grep '/Narralyzer/'`
140 | fi
141 |
142 | if [ -f "$req" ]; then
143 | inform_user "Installing the following packages."
144 | cat "$req"
145 | pip install -r "$req"
146 | fi
147 | fi
148 |
149 | #if [ ! -d 'tika' ]; then
150 | # mkdir tika && cd tika
151 | # get_if_not_there $TIKA
152 | # unzip -q -n `basename "$TIKA"`
153 | # rm `basename "$TIKA"`
154 | #fi
155 |
--------------------------------------------------------------------------------
/site/index.py:
--------------------------------------------------------------------------------
1 | #!/usr/bin/env python2.7
2 |
3 | import os, sys
4 |
5 | sys.path.append(os.path.dirname(__file__))
6 | VIRT_ENV = "env/bin/activate_this.py"
7 | execfile(VIRT_ENV, dict(__file__=VIRT_ENV))
8 |
9 | import codecs
10 | import datetime
11 | import magic
12 | import os
13 | import string
14 | import sys
15 | import sys
16 | import xml.etree.ElementTree as etree
17 |
18 | from collections import Counter
19 | from dateutil.tz import tzlocal
20 | from flask import *
21 | from flask_mako import MakoTemplates
22 | from langdetect import detect
23 | from time import gmtime, strftime
24 | from werkzeug import secure_filename
25 |
26 | UPLOAD_FOLDER = 'upload'
27 |
28 | sys.path.append(os.path.dirname(__file__))
29 |
30 | application = Flask(__name__)
31 | application.debug = True
32 | application.config['UPLOAD_FOLDER'] = UPLOAD_FOLDER
33 |
34 | template_path = os.path.join(os.path.dirname(os.path.abspath(__file__)), 'templates')
35 | application.template_folder = template_path
36 |
37 | mako = MakoTemplates(application)
38 |
39 | ALLOWED_EXTENSIONS = set(['pdf', 'xml', 'txt'])
40 |
41 | def tei_to_chapters(fname):
42 | """ Convert a TEI 2 xml into an array of chapters with text,
43 | and return the title.
44 | """
45 | data = codecs.open(fname,'r', 'utf-8').read().replace(' ', '')
46 |
47 | utf8_parser = etree.XMLParser(encoding='utf-8')
48 | book = etree.fromstring(data.encode('utf-8'), parser=utf8_parser)
49 |
50 | chapters = []
51 | chap_title = ''
52 | text = ''
53 | title = ''
54 |
55 | for item in book.iter():
56 | if item.tag == 'author':
57 | author = item.text
58 | if item.tag == 'title' and not title and item.attrib.get('type') and item.attrib.get('type') == 'main':
59 | title = item.text
60 |
61 | if item.tag == 'head':
62 | if item.attrib and item.attrib.get('rend') and \
63 | item.attrib.get('rend') == 'h2' and not item.text is None:
64 | chap_title = item.text
65 |
66 | if item.tag == 'head':
67 | if item.attrib and item.attrib.get('rend') and \
68 | item.attrib.get('rend') == 'h3' and not item.text is None:
69 | chap_title += '\n' + item.text
70 |
71 | if item.tag == 'div':
72 | if item.attrib and item.attrib.get('type') and \
73 | item.attrib.get('type') == 'chapter':
74 | chapters.append([chap_title, text])
75 | text = ''
76 | chap_title = ''
77 |
78 | if 'rend' in item.attrib and not item.text is None:
79 | text += item.text + "\n"
80 | if item.tag == "p" and not item.text is None:
81 | text += item.text + "\n"
82 |
83 | chapters.append([chap_title, text])
84 | return author, title, chapters
85 |
86 | def tei_check(path_to_file):
87 | """ Returns true if the file is an TEI-xml
88 | The following part of the header must be found in the first 10 lines of the file.
89 | ' where is one of"
20 | @echo " html to make standalone HTML files"
21 | @echo " dirhtml to make HTML files named index.html in directories"
22 | @echo " singlehtml to make a single large HTML file"
23 | @echo " pickle to make pickle files"
24 | @echo " json to make JSON files"
25 | @echo " htmlhelp to make HTML files and a HTML help project"
26 | @echo " qthelp to make HTML files and a qthelp project"
27 | @echo " applehelp to make an Apple Help Book"
28 | @echo " devhelp to make HTML files and a Devhelp project"
29 | @echo " epub to make an epub"
30 | @echo " epub3 to make an epub3"
31 | @echo " latex to make LaTeX files, you can set PAPER=a4 or PAPER=letter"
32 | @echo " latexpdf to make LaTeX files and run them through pdflatex"
33 | @echo " latexpdfja to make LaTeX files and run them through platex/dvipdfmx"
34 | @echo " text to make text files"
35 | @echo " man to make manual pages"
36 | @echo " texinfo to make Texinfo files"
37 | @echo " info to make Texinfo files and run them through makeinfo"
38 | @echo " gettext to make PO message catalogs"
39 | @echo " changes to make an overview of all changed/added/deprecated items"
40 | @echo " xml to make Docutils-native XML files"
41 | @echo " pseudoxml to make pseudoxml-XML files for display purposes"
42 | @echo " linkcheck to check all external links for integrity"
43 | @echo " doctest to run all doctests embedded in the documentation (if enabled)"
44 | @echo " coverage to run coverage check of the documentation (if enabled)"
45 | @echo " dummy to check syntax errors of document sources"
46 |
47 | .PHONY: clean
48 | clean:
49 | rm -rf $(BUILDDIR)/*
50 |
51 | .PHONY: html
52 | html:
53 | $(SPHINXBUILD) -b html $(ALLSPHINXOPTS) $(BUILDDIR)/html
54 | @echo
55 | @echo "Build finished. The HTML pages are in $(BUILDDIR)/html."
56 |
57 | .PHONY: dirhtml
58 | dirhtml:
59 | $(SPHINXBUILD) -b dirhtml $(ALLSPHINXOPTS) $(BUILDDIR)/dirhtml
60 | @echo
61 | @echo "Build finished. The HTML pages are in $(BUILDDIR)/dirhtml."
62 |
63 | .PHONY: singlehtml
64 | singlehtml:
65 | $(SPHINXBUILD) -b singlehtml $(ALLSPHINXOPTS) $(BUILDDIR)/singlehtml
66 | @echo
67 | @echo "Build finished. The HTML page is in $(BUILDDIR)/singlehtml."
68 |
69 | .PHONY: pickle
70 | pickle:
71 | $(SPHINXBUILD) -b pickle $(ALLSPHINXOPTS) $(BUILDDIR)/pickle
72 | @echo
73 | @echo "Build finished; now you can process the pickle files."
74 |
75 | .PHONY: json
76 | json:
77 | $(SPHINXBUILD) -b json $(ALLSPHINXOPTS) $(BUILDDIR)/json
78 | @echo
79 | @echo "Build finished; now you can process the JSON files."
80 |
81 | .PHONY: htmlhelp
82 | htmlhelp:
83 | $(SPHINXBUILD) -b htmlhelp $(ALLSPHINXOPTS) $(BUILDDIR)/htmlhelp
84 | @echo
85 | @echo "Build finished; now you can run HTML Help Workshop with the" \
86 | ".hhp project file in $(BUILDDIR)/htmlhelp."
87 |
88 | .PHONY: qthelp
89 | qthelp:
90 | $(SPHINXBUILD) -b qthelp $(ALLSPHINXOPTS) $(BUILDDIR)/qthelp
91 | @echo
92 | @echo "Build finished; now you can run "qcollectiongenerator" with the" \
93 | ".qhcp project file in $(BUILDDIR)/qthelp, like this:"
94 | @echo "# qcollectiongenerator $(BUILDDIR)/qthelp/Narralyzer.qhcp"
95 | @echo "To view the help file:"
96 | @echo "# assistant -collectionFile $(BUILDDIR)/qthelp/Narralyzer.qhc"
97 |
98 | .PHONY: applehelp
99 | applehelp:
100 | $(SPHINXBUILD) -b applehelp $(ALLSPHINXOPTS) $(BUILDDIR)/applehelp
101 | @echo
102 | @echo "Build finished. The help book is in $(BUILDDIR)/applehelp."
103 | @echo "N.B. You won't be able to view it unless you put it in" \
104 | "~/Library/Documentation/Help or install it in your application" \
105 | "bundle."
106 |
107 | .PHONY: devhelp
108 | devhelp:
109 | $(SPHINXBUILD) -b devhelp $(ALLSPHINXOPTS) $(BUILDDIR)/devhelp
110 | @echo
111 | @echo "Build finished."
112 | @echo "To view the help file:"
113 | @echo "# mkdir -p $$HOME/.local/share/devhelp/Narralyzer"
114 | @echo "# ln -s $(BUILDDIR)/devhelp $$HOME/.local/share/devhelp/Narralyzer"
115 | @echo "# devhelp"
116 |
117 | .PHONY: epub
118 | epub:
119 | $(SPHINXBUILD) -b epub $(ALLSPHINXOPTS) $(BUILDDIR)/epub
120 | @echo
121 | @echo "Build finished. The epub file is in $(BUILDDIR)/epub."
122 |
123 | .PHONY: epub3
124 | epub3:
125 | $(SPHINXBUILD) -b epub3 $(ALLSPHINXOPTS) $(BUILDDIR)/epub3
126 | @echo
127 | @echo "Build finished. The epub3 file is in $(BUILDDIR)/epub3."
128 |
129 | .PHONY: latex
130 | latex:
131 | $(SPHINXBUILD) -b latex $(ALLSPHINXOPTS) $(BUILDDIR)/latex
132 | @echo
133 | @echo "Build finished; the LaTeX files are in $(BUILDDIR)/latex."
134 | @echo "Run \`make' in that directory to run these through (pdf)latex" \
135 | "(use \`make latexpdf' here to do that automatically)."
136 |
137 | .PHONY: latexpdf
138 | latexpdf:
139 | $(SPHINXBUILD) -b latex $(ALLSPHINXOPTS) $(BUILDDIR)/latex
140 | @echo "Running LaTeX files through pdflatex..."
141 | $(MAKE) -C $(BUILDDIR)/latex all-pdf
142 | @echo "pdflatex finished; the PDF files are in $(BUILDDIR)/latex."
143 |
144 | .PHONY: latexpdfja
145 | latexpdfja:
146 | $(SPHINXBUILD) -b latex $(ALLSPHINXOPTS) $(BUILDDIR)/latex
147 | @echo "Running LaTeX files through platex and dvipdfmx..."
148 | $(MAKE) -C $(BUILDDIR)/latex all-pdf-ja
149 | @echo "pdflatex finished; the PDF files are in $(BUILDDIR)/latex."
150 |
151 | .PHONY: text
152 | text:
153 | $(SPHINXBUILD) -b text $(ALLSPHINXOPTS) $(BUILDDIR)/text
154 | @echo
155 | @echo "Build finished. The text files are in $(BUILDDIR)/text."
156 |
157 | .PHONY: man
158 | man:
159 | $(SPHINXBUILD) -b man $(ALLSPHINXOPTS) $(BUILDDIR)/man
160 | @echo
161 | @echo "Build finished. The manual pages are in $(BUILDDIR)/man."
162 |
163 | .PHONY: texinfo
164 | texinfo:
165 | $(SPHINXBUILD) -b texinfo $(ALLSPHINXOPTS) $(BUILDDIR)/texinfo
166 | @echo
167 | @echo "Build finished. The Texinfo files are in $(BUILDDIR)/texinfo."
168 | @echo "Run \`make' in that directory to run these through makeinfo" \
169 | "(use \`make info' here to do that automatically)."
170 |
171 | .PHONY: info
172 | info:
173 | $(SPHINXBUILD) -b texinfo $(ALLSPHINXOPTS) $(BUILDDIR)/texinfo
174 | @echo "Running Texinfo files through makeinfo..."
175 | make -C $(BUILDDIR)/texinfo info
176 | @echo "makeinfo finished; the Info files are in $(BUILDDIR)/texinfo."
177 |
178 | .PHONY: gettext
179 | gettext:
180 | $(SPHINXBUILD) -b gettext $(I18NSPHINXOPTS) $(BUILDDIR)/locale
181 | @echo
182 | @echo "Build finished. The message catalogs are in $(BUILDDIR)/locale."
183 |
184 | .PHONY: changes
185 | changes:
186 | $(SPHINXBUILD) -b changes $(ALLSPHINXOPTS) $(BUILDDIR)/changes
187 | @echo
188 | @echo "The overview file is in $(BUILDDIR)/changes."
189 |
190 | .PHONY: linkcheck
191 | linkcheck:
192 | $(SPHINXBUILD) -b linkcheck $(ALLSPHINXOPTS) $(BUILDDIR)/linkcheck
193 | @echo
194 | @echo "Link check complete; look for any errors in the above output " \
195 | "or in $(BUILDDIR)/linkcheck/output.txt."
196 |
197 | .PHONY: doctest
198 | doctest:
199 | $(SPHINXBUILD) -b doctest $(ALLSPHINXOPTS) $(BUILDDIR)/doctest
200 | @echo "Testing of doctests in the sources finished, look at the " \
201 | "results in $(BUILDDIR)/doctest/output.txt."
202 |
203 | .PHONY: coverage
204 | coverage:
205 | $(SPHINXBUILD) -b coverage $(ALLSPHINXOPTS) $(BUILDDIR)/coverage
206 | @echo "Testing of coverage in the sources finished, look at the " \
207 | "results in $(BUILDDIR)/coverage/python.txt."
208 |
209 | .PHONY: xml
210 | xml:
211 | $(SPHINXBUILD) -b xml $(ALLSPHINXOPTS) $(BUILDDIR)/xml
212 | @echo
213 | @echo "Build finished. The XML files are in $(BUILDDIR)/xml."
214 |
215 | .PHONY: pseudoxml
216 | pseudoxml:
217 | $(SPHINXBUILD) -b pseudoxml $(ALLSPHINXOPTS) $(BUILDDIR)/pseudoxml
218 | @echo
219 | @echo "Build finished. The pseudo-XML files are in $(BUILDDIR)/pseudoxml."
220 |
221 | .PHONY: dummy
222 | dummy:
223 | $(SPHINXBUILD) -b dummy $(ALLSPHINXOPTS) $(BUILDDIR)/dummy
224 | @echo
225 | @echo "Build finished. Dummy builder generates no files."
226 |
--------------------------------------------------------------------------------
/docs/source/conf.py:
--------------------------------------------------------------------------------
1 | # -*- coding: utf-8 -*-
2 | #
3 | # Narralyzer documentation build configuration file, created by
4 | # sphinx-quickstart on Sun Jul 31 13:24:34 2016.
5 | #
6 | # This file is execfile()d with the current directory set to its
7 | # containing dir.
8 | #
9 | # Note that not all possible configuration values are present in this
10 | # autogenerated file.
11 | #
12 | # All configuration values have a default; values that are commented out
13 | # serve to show the default.
14 |
15 | # If extensions (or modules to document with autodoc) are in another directory,
16 | # add these directories to sys.path here. If the directory is relative to the
17 | # documentation root, use os.path.abspath to make it absolute, like shown here.
18 | #
19 | import os
20 | import sys
21 | sys.path.insert(0, os.path.abspath('../'))
22 |
23 | # -- General configuration ------------------------------------------------
24 |
25 | # If your documentation needs a minimal Sphinx version, state it here.
26 | #
27 | # needs_sphinx = '1.0'
28 |
29 | # Add any Sphinx extension module names here, as strings. They can be
30 | # extensions coming with Sphinx (named 'sphinx.ext.*') or your custom
31 | # ones.
32 | extensions = [
33 | 'sphinx.ext.autodoc',
34 | 'sphinx.ext.doctest',
35 | 'sphinx.ext.intersphinx',
36 | 'sphinx.ext.todo',
37 | 'sphinx.ext.coverage',
38 | 'sphinx.ext.mathjax',
39 | 'sphinx.ext.ifconfig',
40 | 'sphinx.ext.viewcode',
41 | 'sphinx.ext.githubpages',
42 | ]
43 |
44 | # Add any paths that contain templates here, relative to this directory.
45 | templates_path = ['_templates']
46 |
47 | # The suffix(es) of source filenames.
48 | # You can specify multiple suffix as a list of string:
49 | #
50 | # source_suffix = ['.rst', '.md']
51 | source_suffix = '.rst'
52 |
53 | # The encoding of source files.
54 | #
55 | # source_encoding = 'utf-8-sig'
56 |
57 | # The master toctree document.
58 | master_doc = 'narralyzer'
59 |
60 | # General information about the project.
61 | project = u'Narralyzer'
62 | copyright = u'2016, Willem Jan Faber'
63 | author = u'Willem Jan Faber'
64 |
65 | # The version info for the project you're documenting, acts as replacement for
66 | # |version| and |release|, also used in various other places throughout the
67 | # built documents.
68 | #
69 | # The short X.Y version.
70 | version = u'0.1'
71 | # The full version, including alpha/beta/rc tags.
72 | release = u'0.1'
73 |
74 | # The language for content autogenerated by Sphinx. Refer to documentation
75 | # for a list of supported languages.
76 | #
77 | # This is also used if you do content translation via gettext catalogs.
78 | # Usually you set "language" from the command line for these cases.
79 | language = None
80 |
81 | # There are two options for replacing |today|: either, you set today to some
82 | # non-false value, then it is used:
83 | #
84 | # today = ''
85 | #
86 | # Else, today_fmt is used as the format for a strftime call.
87 | #
88 | # today_fmt = '%B %d, %Y'
89 |
90 | # List of patterns, relative to source directory, that match files and
91 | # directories to ignore when looking for source files.
92 | # This patterns also effect to html_static_path and html_extra_path
93 | exclude_patterns = []
94 |
95 | # The reST default role (used for this markup: `text`) to use for all
96 | # documents.
97 | #
98 | # default_role = None
99 |
100 | # If true, '()' will be appended to :func: etc. cross-reference text.
101 | #
102 | # add_function_parentheses = True
103 |
104 | # If true, the current module name will be prepended to all description
105 | # unit titles (such as .. function::).
106 | #
107 | # add_module_names = True
108 |
109 | # If true, sectionauthor and moduleauthor directives will be shown in the
110 | # output. They are ignored by default.
111 | #
112 | # show_authors = False
113 |
114 | # The name of the Pygments (syntax highlighting) style to use.
115 | pygments_style = 'sphinx'
116 |
117 | # A list of ignored prefixes for module index sorting.
118 | # modindex_common_prefix = []
119 |
120 | # If true, keep warnings as "system message" paragraphs in the built documents.
121 | # keep_warnings = False
122 |
123 | # If true, `todo` and `todoList` produce output, else they produce nothing.
124 | todo_include_todos = True
125 |
126 |
127 | # -- Options for HTML output ----------------------------------------------
128 |
129 | # The theme to use for HTML and HTML Help pages. See the documentation for
130 | # a list of builtin themes.
131 | #
132 | html_theme = 'classic'
133 |
134 | # Theme options are theme-specific and customize the look and feel of a theme
135 | # further. For a list of options available for each theme, see the
136 | # documentation.
137 | #
138 | # html_theme_options = {}
139 |
140 | # Add any paths that contain custom themes here, relative to this directory.
141 | # html_theme_path = []
142 |
143 | # The name for this set of Sphinx documents.
144 | # " v documentation" by default.
145 | #
146 | html_title = u'Narralyzer v0.1'
147 |
148 | # A shorter title for the navigation bar. Default is the same as html_title.
149 | #
150 | # html_short_title = None
151 |
152 | # The name of an image file (relative to this directory) to place at the top
153 | # of the sidebar.
154 | #
155 | # html_logo = None
156 |
157 | # The name of an image file (relative to this directory) to use as a favicon of
158 | # the docs. This file should be a Windows icon file (.ico) being 16x16 or 32x32
159 | # pixels large.
160 | #
161 | # html_favicon = None
162 |
163 | # Add any paths that contain custom static files (such as style sheets) here,
164 | # relative to this directory. They are copied after the builtin static files,
165 | # so a file named "default.css" will overwrite the builtin "default.css".
166 | html_static_path = ['_static']
167 |
168 | # Add any extra paths that contain custom files (such as robots.txt or
169 | # .htaccess) here, relative to this directory. These files are copied
170 | # directly to the root of the documentation.
171 | #
172 | # html_extra_path = []
173 |
174 | # If not None, a 'Last updated on:' timestamp is inserted at every page
175 | # bottom, using the given strftime format.
176 | # The empty string is equivalent to '%b %d, %Y'.
177 | #
178 | # html_last_updated_fmt = None
179 |
180 | # If true, SmartyPants will be used to convert quotes and dashes to
181 | # typographically correct entities.
182 | #
183 | # html_use_smartypants = True
184 |
185 | # Custom sidebar templates, maps document names to template names.
186 | #
187 | # html_sidebars = {}
188 |
189 | # Additional templates that should be rendered to pages, maps page names to
190 | # template names.
191 | #
192 | # html_additional_pages = {}
193 |
194 | # If false, no module index is generated.
195 | #
196 | # html_domain_indices = True
197 |
198 | # If false, no index is generated.
199 | #
200 | # html_use_index = True
201 |
202 | # If true, the index is split into individual pages for each letter.
203 | #
204 | # html_split_index = False
205 |
206 | # If true, links to the reST sources are added to the pages.
207 | #
208 | # html_show_sourcelink = True
209 |
210 | # If true, "Created using Sphinx" is shown in the HTML footer. Default is True.
211 | #
212 | # html_show_sphinx = True
213 |
214 | # If true, "(C) Copyright ..." is shown in the HTML footer. Default is True.
215 | #
216 | # html_show_copyright = True
217 |
218 | # If true, an OpenSearch description file will be output, and all pages will
219 | # contain a tag referring to it. The value of this option must be the
220 | # base URL from which the finished HTML is served.
221 | #
222 | # html_use_opensearch = ''
223 |
224 | # This is the file name suffix for HTML files (e.g. ".xhtml").
225 | # html_file_suffix = None
226 |
227 | # Language to be used for generating the HTML full-text search index.
228 | # Sphinx supports the following languages:
229 | # 'da', 'de', 'en', 'es', 'fi', 'fr', 'hu', 'it', 'ja'
230 | # 'nl', 'no', 'pt', 'ro', 'ru', 'sv', 'tr', 'zh'
231 | #
232 | # html_search_language = 'en'
233 |
234 | # A dictionary with options for the search language support, empty by default.
235 | # 'ja' uses this config value.
236 | # 'zh' user can custom change `jieba` dictionary path.
237 | #
238 | # html_search_options = {'type': 'default'}
239 |
240 | # The name of a javascript file (relative to the configuration directory) that
241 | # implements a search results scorer. If empty, the default will be used.
242 | #
243 | # html_search_scorer = 'scorer.js'
244 |
245 | # Output file base name for HTML help builder.
246 | htmlhelp_basename = 'Narralyzerdoc'
247 |
248 | # -- Options for LaTeX output ---------------------------------------------
249 |
250 | latex_elements = {
251 | # The paper size ('letterpaper' or 'a4paper').
252 | #
253 | # 'papersize': 'letterpaper',
254 |
255 | # The font size ('10pt', '11pt' or '12pt').
256 | #
257 | # 'pointsize': '10pt',
258 |
259 | # Additional stuff for the LaTeX preamble.
260 | #
261 | # 'preamble': '',
262 |
263 | # Latex figure (float) alignment
264 | #
265 | # 'figure_align': 'htbp',
266 | }
267 |
268 | # Grouping the document tree into LaTeX files. List of tuples
269 | # (source start file, target name, title,
270 | # author, documentclass [howto, manual, or own class]).
271 | latex_documents = [
272 | (master_doc, 'Narralyzer.tex', u'Narralyzer Documentation',
273 | u'Willem Jan Faber', 'manual'),
274 | ]
275 |
276 | # The name of an image file (relative to this directory) to place at the top of
277 | # the title page.
278 | #
279 | # latex_logo = None
280 |
281 | # For "manual" documents, if this is true, then toplevel headings are parts,
282 | # not chapters.
283 | #
284 | # latex_use_parts = False
285 |
286 | # If true, show page references after internal links.
287 | #
288 | # latex_show_pagerefs = False
289 |
290 | # If true, show URL addresses after external links.
291 | #
292 | # latex_show_urls = False
293 |
294 | # Documents to append as an appendix to all manuals.
295 | #
296 | # latex_appendices = []
297 |
298 | # It false, will not define \strong, \code, itleref, \crossref ... but only
299 | # \sphinxstrong, ..., \sphinxtitleref, ... To help avoid clash with user added
300 | # packages.
301 | #
302 | # latex_keep_old_macro_names = True
303 |
304 | # If false, no module index is generated.
305 | #
306 | # latex_domain_indices = True
307 |
308 |
309 | # -- Options for manual page output ---------------------------------------
310 |
311 | # One entry per manual page. List of tuples
312 | # (source start file, name, description, authors, manual section).
313 | man_pages = [
314 | (master_doc, 'narralyzer', u'Narralyzer Documentation',
315 | [author], 1)
316 | ]
317 |
318 | # If true, show URL addresses after external links.
319 | #
320 | # man_show_urls = False
321 |
322 |
323 | # -- Options for Texinfo output -------------------------------------------
324 |
325 | # Grouping the document tree into Texinfo files. List of tuples
326 | # (source start file, target name, title, author,
327 | # dir menu entry, description, category)
328 | texinfo_documents = [
329 | (master_doc, 'Narralyzer', u'Narralyzer Documentation',
330 | author, 'Narralyzer', 'One line description of project.',
331 | 'Miscellaneous'),
332 | ]
333 |
334 | # Documents to append as an appendix to all manuals.
335 | #
336 | # texinfo_appendices = []
337 |
338 | # If false, no module index is generated.
339 | #
340 | # texinfo_domain_indices = True
341 |
342 | # How to display URL addresses: 'footnote', 'no', or 'inline'.
343 | #
344 | # texinfo_show_urls = 'footnote'
345 |
346 | # If true, do not generate a @detailmenu in the "Top" node's menu.
347 | #
348 | # texinfo_no_detailmenu = False
349 |
350 |
351 | # -- Options for Epub output ----------------------------------------------
352 |
353 | # Bibliographic Dublin Core info.
354 | epub_title = project
355 | epub_author = author
356 | epub_publisher = author
357 | epub_copyright = copyright
358 |
359 | # The basename for the epub file. It defaults to the project name.
360 | # epub_basename = project
361 |
362 | # The HTML theme for the epub output. Since the default themes are not
363 | # optimized for small screen space, using the same theme for HTML and epub
364 | # output is usually not wise. This defaults to 'epub', a theme designed to save
365 | # visual space.
366 | #
367 | # epub_theme = 'epub'
368 |
369 | # The language of the text. It defaults to the language option
370 | # or 'en' if the language is not set.
371 | #
372 | # epub_language = ''
373 |
374 | # The scheme of the identifier. Typical schemes are ISBN or URL.
375 | # epub_scheme = ''
376 |
377 | # The unique identifier of the text. This can be a ISBN number
378 | # or the project homepage.
379 | #
380 | # epub_identifier = ''
381 |
382 | # A unique identification for the text.
383 | #
384 | # epub_uid = ''
385 |
386 | # A tuple containing the cover image and cover page html template filenames.
387 | #
388 | # epub_cover = ()
389 |
390 | # A sequence of (type, uri, title) tuples for the guide element of content.opf.
391 | #
392 | # epub_guide = ()
393 |
394 | # HTML files that should be inserted before the pages created by sphinx.
395 | # The format is a list of tuples containing the path and title.
396 | #
397 | # epub_pre_files = []
398 |
399 | # HTML files that should be inserted after the pages created by sphinx.
400 | # The format is a list of tuples containing the path and title.
401 | #
402 | # epub_post_files = []
403 |
404 | # A list of files that should not be packed into the epub file.
405 | epub_exclude_files = ['search.html']
406 |
407 | # The depth of the table of contents in toc.ncx.
408 | #
409 | # epub_tocdepth = 3
410 |
411 | # Allow duplicate toc entries.
412 | #
413 | # epub_tocdup = True
414 |
415 | # Choose between 'default' and 'includehidden'.
416 | #
417 | # epub_tocscope = 'default'
418 |
419 | # Fix unsupported image types using the Pillow.
420 | #
421 | # epub_fix_images = False
422 |
423 | # Scale large images.
424 | #
425 | # epub_max_image_width = 0
426 |
427 | # How to display URL addresses: 'footnote', 'no', or 'inline'.
428 | #
429 | # epub_show_urls = 'inline'
430 |
431 | # If false, no index is generated.
432 | #
433 | # epub_use_index = True
434 |
435 |
436 | # Example configuration for intersphinx: refer to the Python standard library.
437 | intersphinx_mapping = {'https://docs.python.org/': None}
438 |
--------------------------------------------------------------------------------
/narralyzer/stanford_ner_wrapper.py:
--------------------------------------------------------------------------------
1 | #!/usr/bin/env python2.7
2 | # -*- coding: utf-8 -*-
3 | """
4 | narralyzer.stanford_ner_wrapper
5 | ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
6 | Implements tiny wrapper for Stanford CoreNLP NER.
7 | Also invokes the awsome powers of probablepeople!
8 |
9 | Hint's on setting up a high-preformance NER-farm.
10 | http://stanfordnlp.github.io/CoreNLP/corenlp-server.html#dedicated-server
11 |
12 | Docs on probablepeople are found here:
13 | http://probablepeople.readthedocs.io/
14 |
15 | :copyright: (c) 2016 Koninklijke Bibliotheek, by Willem-Jan Faber.
16 | :license: GPLv3, see licence.txt for more details.
17 | """
18 |
19 | import sys
20 | reload(sys)
21 | sys.setdefaultencoding('utf-8')
22 |
23 | import logging
24 | import lxml.html
25 | import probablepeople
26 | import socket
27 | import sys
28 |
29 | from contextlib import contextmanager
30 | from django.utils.encoding import smart_text
31 |
32 | log = logging.basicConfig(stream=sys.stdout, level=logging.INFO)
33 |
34 |
35 | @contextmanager
36 | def _tcpip4_socket(host, port):
37 | """Open a TCP/IP4 socket to designated host/port.
38 | This code originates from 'pip install ner',
39 | but the module itself was broken, so took usefull code
40 | and improved on it.
41 | """
42 |
43 | sock = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
44 | sock.settimeout(50)
45 |
46 | try:
47 | sock.connect((host, port))
48 | yield sock
49 | finally:
50 | try:
51 | sock.shutdown(socket.SHUT_RDWR)
52 | except socket.error:
53 | log.error("Socket error %s %s" % (host, str(port)))
54 | pass
55 | except OSError:
56 | log.error("OSEerror %s %s" % (host, str(port)))
57 | pass
58 | finally:
59 | sock.close()
60 |
61 |
62 | def stanford_ner_wrapper(text, port=False, use_pp=True, host='localhost'):
63 | """
64 | Standalone function to fetch results from Stanford ner, and appy probablepeople.
65 |
66 |
67 | >>> res = stanford_ner_wrapper("Willem-Alexander (Dutch: [ˈʋɪləm aːlɛkˈsɑndər]; Willem-Alexander Claus George Ferdinand; born 27 April 1967) is the King of the Netherlands.", 9991, True)
68 | >>> from pprint import pprint;pprint(res)
69 | {'ners': [{'string': 'Willem-Alexander', 'tag': 'person'},
70 | {'string': 'Willem-Alexander Claus George Ferdinand',
71 | 'tag': 'person'},
72 | {'string': 'Netherlands', 'tag': 'location'}],
73 | 'pp': [{'parse': [('Willem-Alexander', 'GivenName')],
74 | 'tag': {'GivenName': 'Willem-Alexander'}},
75 | {'parse': [('Willem-Alexander', 'CorporationName'),
76 | ('Claus', 'CorporationName'),
77 | ('George', 'CorporationName'),
78 | ('Ferdinand', 'CorporationName')],
79 | 'tag': {'CorporationName': 'Willem-Alexander Claus George Ferdinand'}}],
80 | 'raw_ners': [{'string': 'Willem-Alexander', 'tag': 'person'},
81 | {'string': 'Willem-Alexander Claus George Ferdinand',
82 | 'tag': 'person'},
83 | {'string': 'Netherlands', 'tag': 'location'}],
84 | 'raw_response': u'Willem-Alexander (Dutch: [\u02c8\u028b\u026al\u0259m a\u02d0l\u025bk\u02c8s\u0251nd\u0259r]; Willem-Alexander Claus George Ferdinand; born 27 April 1967) is the King of the Netherlands.'}
85 | >>> res = stanford_ner_wrapper("Prof. Albert Einstein vertoeft op het oogenblik te Londen, en gisteravond was hij in Savoy Hotel eeregast aan een diner, gegeven door de Ort and Oze Societies. De voorzitter van de Engelsche sectie dier Vereeniging is Lord • Rothschild ; de voorzitter van de Duitsche sectie is prof. Einstein. Lord Rothschild presideerde het diner; aan zijn rechterhand zat de beroemdste geleerde van onzen tyd, aan zijn linkerhand de beroemdste dichter, Bernard Shaw. Rechts van Einstein zat Wells. Het was een gastmaal voor het intellect en z|jn dames. Ik wil er geen verslag van geven, maar my bepalen tot enkele aanteekeningen.", 9993, True)
86 | >>> from pprint import pprint;pprint(res)
87 | {'ners': [{'string': 'Albert Einstein', 'tag': 'per'},
88 | {'string': 'Londen', 'tag': 'loc'},
89 | {'string': 'Savoy Hotel', 'tag': 'loc'},
90 | {'string': 'Ort and Oze Societies', 'tag': 'misc'},
91 | {'string': 'Engelsche', 'tag': 'misc'},
92 | {'string': 'Vereeniging', 'tag': 'loc'},
93 | {'string': u'Lord \u2022 Rothschild', 'tag': 'per'},
94 | {'string': 'Duitsche', 'tag': 'misc'},
95 | {'string': 'Einstein', 'tag': 'loc'},
96 | {'string': 'Lord Rothschild', 'tag': 'per'},
97 | {'string': 'Bernard Shaw', 'tag': 'per'},
98 | {'string': 'Einstein', 'tag': 'loc'},
99 | {'string': 'Wells', 'tag': 'per'}],
100 | 'pp': [{'parse': [('Albert', 'GivenName'), ('Einstein', 'Surname')],
101 | 'tag': {'GivenName': 'Albert', 'Surname': 'Einstein'}},
102 | {'parse': [(u'Lord', 'GivenName'), (u'Rothschild', 'Surname')],
103 | 'tag': {'GivenName': u'Lord', 'Surname': u'Rothschild'}},
104 | {'parse': [('Lord', 'GivenName'), ('Rothschild', 'Surname')],
105 | 'tag': {'GivenName': 'Lord', 'Surname': 'Rothschild'}},
106 | {'parse': [('Bernard', 'GivenName'), ('Shaw', 'Surname')],
107 | 'tag': {'GivenName': 'Bernard', 'Surname': 'Shaw'}},
108 | {'parse': [('Wells', 'Surname')], 'tag': {'Surname': 'Wells'}}],
109 | 'raw_ners': [{'string': 'Albert', 'tag': 'b-per'},
110 | {'string': 'Einstein', 'tag': 'i-per'},
111 | {'string': 'Londen', 'tag': 'b-loc'},
112 | {'string': 'Savoy', 'tag': 'b-loc'},
113 | {'string': 'Hotel', 'tag': 'i-loc'},
114 | {'string': 'Ort', 'tag': 'b-misc'},
115 | {'string': 'and Oze Societies', 'tag': 'i-misc'},
116 | {'string': 'Engelsche', 'tag': 'b-misc'},
117 | {'string': 'Vereeniging', 'tag': 'b-loc'},
118 | {'string': 'Lord', 'tag': 'b-per'},
119 | {'string': u'\u2022 Rothschild', 'tag': 'i-per'},
120 | {'string': 'Duitsche', 'tag': 'b-misc'},
121 | {'string': 'Einstein', 'tag': 'b-loc'},
122 | {'string': 'Lord', 'tag': 'b-per'},
123 | {'string': 'Rothschild', 'tag': 'i-per'},
124 | {'string': 'Bernard', 'tag': 'b-per'},
125 | {'string': 'Shaw', 'tag': 'i-per'},
126 | {'string': 'Einstein', 'tag': 'b-loc'},
127 | {'string': 'Wells', 'tag': 'b-per'}],
128 | 'raw_response': u'Prof. AlbertEinstein vertoeft op het oogenblik te Londen, en gisteravond was hij in SavoyHotel eeregast aan een diner, gegeven door de Ortand Oze Societies. De voorzitter van de Engelsche sectie dier Vereeniging is Lord\u2022 Rothschild ; de voorzitter van de Duitsche sectie is prof. Einstein. LordRothschild presideerde het diner; aan zijn rechterhand zat de beroemdste geleerde van onzen tyd, aan zijn linkerhand de beroemdste dichter, BernardShaw. Rechts van Einstein zat Wells. Het was een gastmaal voor het intellect en z|jn dames. Ik wil er geen verslag van geven, maar my bepalen tot enkele aanteekeningen.'}
129 | >>> res = stanford_ner_wrapper("Prof. Albert Einstein vertoeft op het oogenblik te Londen, en gisteravond was hij in Savoy Hotel eeregast aan een diner, gegeven door de Ort and Oze Societies. De voorzitter van de Engelsche sectie dier Vereeniging is Lord • Rothschild ; de voorzitter van de Duitsche sectie is prof. Einstein. Lord Rothschild presideerde het diner; aan zijn rechterhand zat de beroemdste geleerde van onzen tyd, aan zijn linkerhand de beroemdste dichter, Bernard Shaw. Rechts van Einstein zat Wells. Het was een gastmaal voor het intellect en z|jn dames. Ik wil er geen verslag van geven, maar my bepalen tot enkele aanteekeningen.", 9993, True)
130 | >>> from pprint import pprint;pprint(res)
131 | {'ners': [{'string': 'Albert Einstein', 'tag': 'per'},
132 | {'string': 'Londen', 'tag': 'loc'},
133 | {'string': 'Savoy Hotel', 'tag': 'loc'},
134 | {'string': 'Ort and Oze Societies', 'tag': 'misc'},
135 | {'string': 'Engelsche', 'tag': 'misc'},
136 | {'string': 'Vereeniging', 'tag': 'loc'},
137 | {'string': u'Lord \u2022 Rothschild', 'tag': 'per'},
138 | {'string': 'Duitsche', 'tag': 'misc'},
139 | {'string': 'Einstein', 'tag': 'loc'},
140 | {'string': 'Lord Rothschild', 'tag': 'per'},
141 | {'string': 'Bernard Shaw', 'tag': 'per'},
142 | {'string': 'Einstein', 'tag': 'loc'},
143 | {'string': 'Wells', 'tag': 'per'}],
144 | 'pp': [{'parse': [('Albert', 'GivenName'), ('Einstein', 'Surname')],
145 | 'tag': {'GivenName': 'Albert', 'Surname': 'Einstein'}},
146 | {'parse': [(u'Lord', 'GivenName'), (u'Rothschild', 'Surname')],
147 | 'tag': {'GivenName': u'Lord', 'Surname': u'Rothschild'}},
148 | {'parse': [('Lord', 'GivenName'), ('Rothschild', 'Surname')],
149 | 'tag': {'GivenName': 'Lord', 'Surname': 'Rothschild'}},
150 | {'parse': [('Bernard', 'GivenName'), ('Shaw', 'Surname')],
151 | 'tag': {'GivenName': 'Bernard', 'Surname': 'Shaw'}},
152 | {'parse': [('Wells', 'Surname')], 'tag': {'Surname': 'Wells'}}],
153 | 'raw_ners': [{'string': 'Albert', 'tag': 'b-per'},
154 | {'string': 'Einstein', 'tag': 'i-per'},
155 | {'string': 'Londen', 'tag': 'b-loc'},
156 | {'string': 'Savoy', 'tag': 'b-loc'},
157 | {'string': 'Hotel', 'tag': 'i-loc'},
158 | {'string': 'Ort', 'tag': 'b-misc'},
159 | {'string': 'and Oze Societies', 'tag': 'i-misc'},
160 | {'string': 'Engelsche', 'tag': 'b-misc'},
161 | {'string': 'Vereeniging', 'tag': 'b-loc'},
162 | {'string': 'Lord', 'tag': 'b-per'},
163 | {'string': u'\u2022 Rothschild', 'tag': 'i-per'},
164 | {'string': 'Duitsche', 'tag': 'b-misc'},
165 | {'string': 'Einstein', 'tag': 'b-loc'},
166 | {'string': 'Lord', 'tag': 'b-per'},
167 | {'string': 'Rothschild', 'tag': 'i-per'},
168 | {'string': 'Bernard', 'tag': 'b-per'},
169 | {'string': 'Shaw', 'tag': 'i-per'},
170 | {'string': 'Einstein', 'tag': 'b-loc'},
171 | {'string': 'Wells', 'tag': 'b-per'}],
172 | 'raw_response': u'Prof. AlbertEinstein vertoeft op het oogenblik te Londen, en gisteravond was hij in SavoyHotel eeregast aan een diner, gegeven door de Ortand Oze Societies. De voorzitter van de Engelsche sectie dier Vereeniging is Lord\u2022 Rothschild ; de voorzitter van de Duitsche sectie is prof. Einstein. LordRothschild presideerde het diner; aan zijn rechterhand zat de beroemdste geleerde van onzen tyd, aan zijn linkerhand de beroemdste dichter, BernardShaw. Rechts van Einstein zat Wells. Het was een gastmaal voor het intellect en z|jn dames. Ik wil er geen verslag van geven, maar my bepalen tot enkele aanteekeningen.'}
173 | """
174 | for s in ("\f", "\n", "\r", "\t", "\v"): # strip whitespaces
175 | text = text.replace(s, '')
176 | text += "\n" # ensure end-of-line
177 |
178 | with _tcpip4_socket(host, port) as s:
179 | if not isinstance(text, bytes):
180 | text = text.encode('utf-8')
181 | s.sendall(text)
182 |
183 | tagged_text = s.recv(10*len(text))
184 |
185 | result = tagged_text.decode("utf-8")
186 |
187 | ner = {"raw_response": result,
188 | "raw_ners": [],
189 | "ners": []}
190 |
191 | result = "%s" % result
192 | res = lxml.html.fromstring(result)
193 |
194 | for item in res.iter():
195 | if item.tag == 'xml':
196 | continue
197 | ner["raw_ners"].append({"string": item.text,
198 | "tag": item.tag})
199 |
200 | counter_ners = 0
201 | ners = []
202 | for item in ner["raw_ners"]:
203 | if item.get("tag")[0] == 'i':
204 | if counter_ners and len(ners) >= counter_ners - 1:
205 | ners[counter_ners - 1]["string"] += ' ' + item.get("string")
206 | else:
207 | tag = item.get("tag")
208 | if "-" in tag:
209 | tag = tag.split('-')[1]
210 | ners.append({"string": item.get("string"),
211 | "tag": tag})
212 | counter_ners += 1
213 | ner["ners"] = ners
214 |
215 | # Apply probablepeople / (parse and tag)
216 | if use_pp:
217 | pp = []
218 | for item in ners:
219 | if "per" in item["tag"].lower():
220 | result = {}
221 | try:
222 | result["parse"] = probablepeople.parse(item["string"])
223 | for key, value in probablepeople.tag(item["string"])[0].iteritems():
224 | if "tag" not in result:
225 | result["tag"] = {}
226 | if key not in result["tag"]:
227 | result["tag"][key] = value
228 | else:
229 | result["tag"][key] += " " + value
230 | except:
231 | if "error" not in result:
232 | result["error"] = 0
233 | else:
234 | result["error"] += 1
235 | pp.append(result)
236 | ner["pp"] = pp
237 | return ner
238 |
239 |
240 | if __name__ == '__main__':
241 | if len(sys.argv) >= 2 and 'test' in " ".join(sys.argv):
242 | import doctest
243 | doctest.testmod(verbose=True)
244 |
245 | if len(sys.argv) >= 2 and 'profile' in " ".join(sys.argv):
246 | from gutenberg.acquire import load_etext
247 | from gutenberg.cleanup import strip_headers
248 | from pycallgraph import PyCallGraph
249 | from pycallgraph.output import GraphvizOutput
250 |
251 | text = smart_text(strip_headers(load_etext(17685)).strip())
252 | with PyCallGraph(output=GraphvizOutput()):
253 | stanford_ner_wrapper(text, 9992, True)
254 |
--------------------------------------------------------------------------------
/narralyzer/lang_lib.py:
--------------------------------------------------------------------------------
1 | #!/usr/bin/env python2.7
2 | # -*- coding: utf-8 -*-
3 | """
4 | narralyzer.lang_lib
5 | ~~~~~~~~~~~~~~~~~~~
6 | Implements sentence level analyzer for natural language
7 |
8 | :copyright: (c) 2016 Koninklijke Bibliotheek, by Willem Jan Faber.
9 | :license: GPLv3, see licence.txt for more details.
10 | """
11 |
12 | import sys
13 | reload(sys)
14 | sys.setdefaultencoding('utf-8')
15 |
16 | import importlib
17 | import string
18 |
19 | from langdetect import detect
20 | from numpy import mean
21 | from Queue import Queue
22 | from segtok.segmenter import split_multi
23 | from stanford_ner_wrapper import stanford_ner_wrapper
24 | from threading import Thread
25 |
26 | try:
27 | from narralyzer import config
28 | except:
29 | import config
30 |
31 | try:
32 | from narralyzer import utils
33 | except:
34 | import utils
35 |
36 | # TODO Move this to a seperate config module.
37 | STANFORD_NER_SERVERS = {"de": 9990,
38 | "en": 9991,
39 | "fr": 9992,
40 | "nl": 9993,
41 | "sp": 9994}
42 |
43 |
44 | class Language:
45 | '''
46 | Intro
47 | -----
48 | The ``lang_lib.Language`` class is part of the Narralyzer project.
49 | This class takes care of chopping up strings/documents into sentences,
50 | and applies the following:
51 |
52 | - Part-of-speech tagging (Using CLiPS-pattern)
53 | - Sentencte analysis (Using CLiPS-pattern)
54 | - Named entity extraction (Using Stanford CoreNLP)
55 |
56 | About
57 | -----
58 | The module combines the power of several awesome Python/Java projects,
59 | see overview of most relevant projects below.
60 |
61 | Using ``lang_lib.Language``
62 | ---------------------------
63 | >>> lang = Language(("Willem-Jan Faber just invoked lang_lib.Language, while wishing he was in West Virginia."))
64 | Using detected language 'en' to parse input text.
65 | >>> lang.parse()
66 | >>> from pprint import pprint; pprint(lang.result)
67 | {'lang': u'en',
68 | 'sentences': {0: {'count': 0,
69 | 'pos': [{'string': u'Willem-Jan', 'tag': u'NNP'},
70 | {'string': u'Faber', 'tag': u'NNP'},
71 | {'string': u'just', 'tag': u'RB'},
72 | {'string': u'invoked', 'tag': u'VBN'},
73 | {'string': u'lang_lib.Language', 'tag': u'NN'},
74 | {'string': u',', 'tag': u','},
75 | {'string': u'while', 'tag': u'IN'},
76 | {'string': u'wishing', 'tag': u'VBG'},
77 | {'string': u'he', 'tag': u'PRP'},
78 | {'string': u'was', 'tag': u'VBD'},
79 | {'string': u'in', 'tag': u'IN'},
80 | {'string': u'West', 'tag': u'NNP'},
81 | {'string': u'Virginia', 'tag': u'NNP'},
82 | {'string': u'.', 'tag': u'.'}],
83 | 'sentiment': (0.0, 0.0),
84 | 'stanford': {'ners': [{'string': 'Willem-Jan Faber',
85 | 'tag': 'person'},
86 | {'string': 'West Virginia',
87 | 'tag': 'location'}],
88 | 'pp': [{'parse': [('Willem-Jan',
89 | 'GivenName'),
90 | ('Faber', 'Surname')],
91 | 'tag': {'GivenName': 'Willem-Jan',
92 | 'Surname': 'Faber'}}],
93 | 'raw_ners': [{'string': 'Willem-Jan Faber',
94 | 'tag': 'person'},
95 | {'string': 'West Virginia',
96 | 'tag': 'location'}],
97 | 'raw_response': u'Willem-Jan Faber just invoked lang_lib.Language, while wishing he was in West Virginia.'},
98 | 'stats': {'ascii_lowercase': 71,
99 | 'count': 87,
100 | 'digits': 0,
101 | 'lowercase': 65,
102 | 'printable': 87,
103 | 'unprintable': 0,
104 | 'uppercase': 6},
105 | 'string': u'Willem-Jan Faber just invoked lang_lib.Language, while wishing he was in West Virginia.'}},
106 | 'stats': {'avg_length': 87, 'max': 87, 'min': 87},
107 | 'text': 'Willem-Jan Faber just invoked lang_lib.Language, while wishing he was in West Virginia.'}
108 |
109 | URL + Project / Function within Narralyzer:
110 | -------------------------------------------
111 |
112 | http://stanfordnlp.github.io/CoreNLP/
113 | Stanford CoreNLP / Find named entities.
114 | Provide (NER) language models.
115 |
116 | http://www.cnts.ua.ac.be/conll2002/ner/data/
117 | Conference on Computational Natural Language Learning (CoNLL-2002) /
118 | Provide Dutch language model.
119 |
120 | http://www.clips.ua.ac.be/pattern
121 | CLiPS Pattern / Sentiment analysis.
122 | Part-of-speech tagging.
123 |
124 | http://fnl.es/segtok-a-segmentation-and-tokenization-library.html
125 | Segtok / Sentencte segmentation.
126 |
127 | https://github.com/datamade/probablepeople
128 | probablepeople / Verify & split names.
129 |
130 |
131 | Source code: https://github.com/KBNLresearch/Narralyzer
132 | '''
133 | sentences = {}
134 | stanford_port = 9990
135 |
136 | use_threads = False
137 | nr_of_threads = 10
138 |
139 | use_stats = True
140 |
141 | sentiment_avail = True
142 | config = config.Config()
143 |
144 | def __init__(self, text=False, lang=False, use_langdetect=True):
145 | if not text:
146 | msg = "Did not get any text to look at."
147 | print(msg)
148 | sys.exit(-1)
149 |
150 | if len(text) < 9:
151 | msg = "Input text is way to small to say someting credible about it."
152 | print(msg)
153 | sys.exit(-1)
154 |
155 | detected_lang = False
156 | if use_langdetect and not lang:
157 | try:
158 | detected_lang = detect(text)
159 | if detected_lang not in STANFORD_NER_SERVERS:
160 | msg = "Detected language (%s) is not (yet) supported.\n" % detected_lang
161 | print(msg)
162 |
163 | msg = "Using detected language '%s' to parse input text." % detected_lang
164 | print(msg)
165 | lang = detected_lang
166 | except:
167 | msg = "Could not automaticly detect language."
168 | print(msg)
169 | elif use_langdetect and lang:
170 | msg = "Skipping language detection, user specified %s as language" % lang
171 | print(msg)
172 |
173 | if not lang or lang not in self.config.get('supported_languages').lower():
174 | msg = "Did not find suitable language to parse text in."
175 | print(msg, lang)
176 | sys.exit(-1)
177 |
178 | self.stanford_port = STANFORD_NER_SERVERS.get(lang)
179 |
180 | pattern = False
181 | try:
182 | pattern = importlib.import_module('pattern.' + lang)
183 | except:
184 | msg = "Requested language is not (yet) supported, failed to import pattern.%s" % lang
185 | print(msg)
186 | sys.exit(-1)
187 |
188 | self._pattern_parse = pattern.parse
189 |
190 | try:
191 | self._pattern_sentiment = pattern.sentiment
192 | except:
193 | self.sentiment_avail = False
194 |
195 | self._pattern_tag = pattern.tag
196 |
197 | self.result = {"text": text,
198 | "lang": lang,
199 | "sentences": {},
200 | "stats": {}}
201 |
202 | def parse(self):
203 | for count, sentence in enumerate(split_multi(self.result["text"])):
204 | self.result["sentences"][count] = {"string": sentence,
205 | "pos": [],
206 | "sentiment": [],
207 | "stanford": [],
208 | "count": count}
209 |
210 | if self.use_threads:
211 | self._threaded_parser()
212 | else:
213 | self._parser()
214 |
215 | if self.use_stats:
216 | self.stats_all()
217 |
218 | def _parser(self):
219 | for count, sentence in enumerate(self.result["sentences"].values()):
220 | sentence = sentence.get("string")
221 | result = self._parse_singleton(sentence, count)
222 | for item in result:
223 | self.result["sentences"][count][item] = result[item]
224 |
225 | def _threaded_parser(self):
226 | work_queue = Queue()
227 | result_queue = Queue()
228 |
229 | for count, sentence in enumerate(self.result["sentences"].values()):
230 | work_queue.put({"string": sentence.get("string"),
231 | "count": sentence.get("count")})
232 |
233 | nr_of_threads = self.nr_of_threads
234 | if len(self.result["sentences"]) <= self.nr_of_threads:
235 | nr_of_threads = len(self.result["sentences"])
236 |
237 | threads = []
238 | for worker in range(nr_of_threads):
239 | process = Thread(target=self._parse_queue,
240 | args=(work_queue, result_queue))
241 | process.daemon = True
242 | process.start()
243 | threads.append(process)
244 |
245 | for thread in threads:
246 | thread.join()
247 |
248 | try:
249 | result = result_queue.get_nowait()
250 | except:
251 | msg = "Thread did not recieve input from queue, bye!"
252 | print(msg)
253 | result = False
254 |
255 | while result:
256 | count = result.get('count')
257 | for item in result:
258 | if item == 'count':
259 | continue
260 | self.result["sentences"][count][item] = result.get(item)
261 | try:
262 | result = result_queue.get_nowait()
263 | except:
264 | result = False
265 |
266 | def _parse_queue(self, work_queue, done_queue):
267 | done = False
268 | while not done:
269 | try:
270 | job = work_queue.get_nowait()
271 | result = self._parse_singleton(job.get('string'),
272 | job.get('count'))
273 | done_queue.put(result)
274 | except:
275 | done = True
276 |
277 | def _parse_singleton(self, sentence, count):
278 | result = {"count": count,
279 | "pos": False,
280 | "sentiment": False,
281 | "stanford": False,
282 | "stats": False}
283 |
284 | if len(sentence) < 2:
285 | return result
286 |
287 | if self.sentiment_avail:
288 | result["sentiment"] = self._pattern_sentiment(sentence)
289 |
290 | result["stanford"] = stanford_ner_wrapper(sentence,
291 | port=self.stanford_port,
292 | use_pp=True)
293 |
294 | pos = []
295 | for word, pos_tag in self._pattern_tag(sentence):
296 | pos.append({"string": word, "tag": pos_tag})
297 |
298 | result["pos"] = pos
299 |
300 | return result
301 |
302 | def stats_pos(self):
303 | pass
304 |
305 | def stats_ner(self):
306 | pass
307 |
308 | @staticmethod
309 | def stats_sentence(sentence):
310 | ascii_letters = count = digits = lowercase = \
311 | printable = uppercase = unprintable = 0
312 |
313 | for count, char in enumerate(sentence):
314 | if char in string.printable:
315 | printable += 1
316 | if char in string.digits:
317 | digits += 1
318 | elif char in string.ascii_letters:
319 | ascii_letters += 1
320 | if char in string.ascii_lowercase:
321 | lowercase += 1
322 | elif char in string.ascii_uppercase:
323 | uppercase += 1
324 | else:
325 | unprintable += 1
326 |
327 | stats = {"ascii_lowercase": ascii_letters,
328 | "count": count + 1, # a='123'; for i in enumerate(a): print(i)
329 | "digits": digits,
330 | "lowercase": lowercase,
331 | "printable": printable,
332 | "uppercase": uppercase,
333 | "unprintable": unprintable}
334 |
335 | return stats
336 |
337 | def stats_all(self):
338 | max_len = min_len = 0 # Min and max sentence length.
339 | avg = [] # Caluclate average sentence length.
340 | for sentence in self.result["sentences"].values():
341 | # Caluclate the stats per sentence.
342 | sentence_stats = self.stats_sentence(sentence.get("string"))
343 | avg.append(sentence_stats.get("count"))
344 |
345 | if sentence_stats.get("count") > max_len:
346 | max_len = sentence_stats.get("count")
347 |
348 | if sentence_stats.get("count") < min_len:
349 | min_len = sentence_stats.get("count")
350 |
351 | if min_len == 0:
352 | min_len = sentence_stats.get("count")
353 |
354 | self.result["sentences"][sentence.get("count")]["stats"] = sentence_stats
355 |
356 | # Caluclate the total stats.
357 | avg_sentence_length = int(round(mean(avg)))
358 |
359 | stats = {}
360 | stats["avg_length"] = avg_sentence_length
361 | stats["max"] = max_len
362 | stats["min"] = min_len
363 |
364 | self.result["stats"] = stats
365 |
366 |
367 | def _test_NL():
368 | '''
369 | >>> lang = Language("Later gaf Christophorus Columbus in een brief aan Ferdinand en Isabella de opdracht de buit te verstoppen en de haven af te branden. Toen Columbus uit de haven van Tunis voer zag hij de soldaten van Isabella naderen.")
370 | Using detected language 'nl' to parse input text.
371 | >>> lang.use_threads = False
372 | >>> lang.parse()
373 | >>> from pprint import pprint
374 | >>> pprint (lang.result)
375 | {'lang': u'nl',
376 | 'sentences': {0: {'count': 0,
377 | 'pos': [{'string': u'Later', 'tag': u'JJR'},
378 | {'string': u'gaf', 'tag': u'VBD'},
379 | {'string': u'Christophorus', 'tag': u'NNP'},
380 | {'string': u'Columbus', 'tag': u'NNP'},
381 | {'string': u'in', 'tag': u'IN'},
382 | {'string': u'een', 'tag': u'DT'},
383 | {'string': u'brief', 'tag': u'NN'},
384 | {'string': u'aan', 'tag': u'IN'},
385 | {'string': u'Ferdinand', 'tag': u'NNP'},
386 | {'string': u'en', 'tag': u'CC'},
387 | {'string': u'Isabella', 'tag': u'NNP'},
388 | {'string': u'de', 'tag': u'DT'},
389 | {'string': u'opdracht', 'tag': u'NN'},
390 | {'string': u'de', 'tag': u'DT'},
391 | {'string': u'buit', 'tag': u'NN'},
392 | {'string': u'te', 'tag': u'TO'},
393 | {'string': u'verstoppen', 'tag': u'VB'},
394 | {'string': u'en', 'tag': u'CC'},
395 | {'string': u'de', 'tag': u'DT'},
396 | {'string': u'haven', 'tag': u'NN'},
397 | {'string': u'af', 'tag': u'RP'},
398 | {'string': u'te', 'tag': u'TO'},
399 | {'string': u'branden', 'tag': u'VBP'},
400 | {'string': u'.', 'tag': u'.'}],
401 | 'sentiment': (0.0, 0.1),
402 | 'stanford': {'ners': [{'string': 'Christophorus Columbus',
403 | 'tag': 'per'},
404 | {'string': 'Ferdinand',
405 | 'tag': 'loc'},
406 | {'string': 'Isabella',
407 | 'tag': 'per'}],
408 | 'pp': [{'parse': [('Christophorus',
409 | 'CorporationName'),
410 | ('Columbus',
411 | 'CorporationName')],
412 | 'tag': {'CorporationName': 'Christophorus Columbus'}},
413 | {'parse': [('Isabella',
414 | 'GivenName')],
415 | 'tag': {'GivenName': 'Isabella'}}],
416 | 'raw_ners': [{'string': 'Christophorus',
417 | 'tag': 'b-per'},
418 | {'string': 'Columbus',
419 | 'tag': 'i-per'},
420 | {'string': 'Ferdinand',
421 | 'tag': 'b-loc'},
422 | {'string': 'Isabella',
423 | 'tag': 'b-per'}],
424 | 'raw_response': u'Later gaf ChristophorusColumbus in een brief aan Ferdinand en Isabella de opdracht de buit te verstoppen en de haven af te branden.'},
425 | 'stats': {'ascii_lowercase': 109,
426 | 'count': 132,
427 | 'digits': 0,
428 | 'lowercase': 104,
429 | 'printable': 132,
430 | 'unprintable': 0,
431 | 'uppercase': 5},
432 | 'string': u'Later gaf Christophorus Columbus in een brief aan Ferdinand en Isabella de opdracht de buit te verstoppen en de haven af te branden.'},
433 | 1: {'count': 1,
434 | 'pos': [{'string': u'Toen', 'tag': u'CC'},
435 | {'string': u'Columbus', 'tag': u'NNP'},
436 | {'string': u'uit', 'tag': u'IN'},
437 | {'string': u'de', 'tag': u'DT'},
438 | {'string': u'haven', 'tag': u'NN'},
439 | {'string': u'van', 'tag': u'IN'},
440 | {'string': u'Tunis', 'tag': u'NNP'},
441 | {'string': u'voer', 'tag': u'NN'},
442 | {'string': u'zag', 'tag': u'VBD'},
443 | {'string': u'hij', 'tag': u'PRP'},
444 | {'string': u'de', 'tag': u'DT'},
445 | {'string': u'soldaten', 'tag': u'NNS'},
446 | {'string': u'van', 'tag': u'IN'},
447 | {'string': u'Isabella', 'tag': u'NNP'},
448 | {'string': u'naderen', 'tag': u'VB'},
449 | {'string': u'.', 'tag': u'.'}],
450 | 'sentiment': (0.0, 0.0),
451 | 'stanford': {'ners': [{'string': 'Columbus',
452 | 'tag': 'per'},
453 | {'string': 'Tunis', 'tag': 'loc'},
454 | {'string': 'Isabella',
455 | 'tag': 'per'}],
456 | 'pp': [{'parse': [('Columbus',
457 | 'GivenName')],
458 | 'tag': {'GivenName': 'Columbus'}},
459 | {'parse': [('Isabella',
460 | 'GivenName')],
461 | 'tag': {'GivenName': 'Isabella'}}],
462 | 'raw_ners': [{'string': 'Columbus',
463 | 'tag': 'b-per'},
464 | {'string': 'Tunis',
465 | 'tag': 'b-loc'},
466 | {'string': 'Isabella',
467 | 'tag': 'b-per'}],
468 | 'raw_response': u'Toen Columbus uit de haven van Tunis voer zag hij de soldaten van Isabella naderen.'},
469 | 'stats': {'ascii_lowercase': 68,
470 | 'count': 83,
471 | 'digits': 0,
472 | 'lowercase': 64,
473 | 'printable': 83,
474 | 'unprintable': 0,
475 | 'uppercase': 4},
476 | 'string': u'Toen Columbus uit de haven van Tunis voer zag hij de soldaten van Isabella naderen.'}},
477 | 'stats': {'avg_length': 108, 'max': 132, 'min': 83},
478 | 'text': 'Later gaf Christophorus Columbus in een brief aan Ferdinand en Isabella de opdracht de buit te verstoppen en de haven af te branden. Toen Columbus uit de haven van Tunis voer zag hij de soldaten van Isabella naderen.'}
479 | '''
480 | lang = Language("Later gaf Christophorus Columbus in een brief aan Ferdinand en Isabella de opdracht de buit te verstoppen en de haven af te branden. Toen Columbus uit de haven van Tunis voer zag hij de soldaten van Isabella naderen.", "nl")
481 | lang.use_threads = False
482 | lang.parse()
483 | from pprint import pprint
484 | pprint(lang.result)
485 |
486 | if __name__ == '__main__':
487 | if len(sys.argv) >= 2 and "test" in " ".join(sys.argv):
488 | import doctest
489 | doctest.testmod(verbose=True)
490 |
491 | if len(sys.argv) >= 2 and "time" or "profile" in " ".join(sys.argv):
492 | import time
493 | import json
494 |
495 | from django.utils.encoding import smart_text
496 | from gutenberg.acquire import load_etext
497 | from gutenberg.cleanup import strip_headers
498 | from pycallgraph import PyCallGraph
499 | from pycallgraph.output import GraphvizOutput
500 |
501 | if "time" in " ".join(sys.argv):
502 | print("Timing non-threaded lang_lib")
503 | s = time.time()
504 | lang = Language(text)
505 | lang.use_threads = False
506 | lang.parse()
507 | print("Took %s seconds" % (str(round(s - time.time()) * -1)))
508 |
509 | print("Timing threaded lang_lib")
510 | s = time.time()
511 | lang = Language(text)
512 | lang.use_threads = True
513 | lang.parse()
514 | print("Took %s seconds" % (str(round(s - time.time()) * -1)))
515 |
516 | print("Timing ner-vanilla")
517 | s = time.time()
518 | stanford_ner_wrapper(text, 9992)
519 | print("Took %s seconds" % (str(round(s - time.time()) * -1)))
520 |
521 | outfile = "../out/%s.pos_ner_sentiment.json" % gutenberg_test_id
522 | print("Writing output in json-format to: %s" % outfile)
523 | with open(outfile, "w") as fh:
524 | fh.write(json.dumps(lang.result))
525 |
526 | with PyCallGraph(output=GraphvizOutput()):
527 | lang = Language(text)
528 | lang.use_threads = True
529 | lang.parse()
530 |
--------------------------------------------------------------------------------
/licence.txt:
--------------------------------------------------------------------------------
1 | GNU GENERAL PUBLIC LICENSE
2 | Version 3, 29 June 2007
3 |
4 | Copyright (C) 2007 Free Software Foundation, Inc.
5 | Everyone is permitted to copy and distribute verbatim copies
6 | of this license document, but changing it is not allowed.
7 |
8 | Preamble
9 |
10 | The GNU General Public License is a free, copyleft license for
11 | software and other kinds of works.
12 |
13 | The licenses for most software and other practical works are designed
14 | to take away your freedom to share and change the works. By contrast,
15 | the GNU General Public License is intended to guarantee your freedom to
16 | share and change all versions of a program--to make sure it remains free
17 | software for all its users. We, the Free Software Foundation, use the
18 | GNU General Public License for most of our software; it applies also to
19 | any other work released this way by its authors. You can apply it to
20 | your programs, too.
21 |
22 | When we speak of free software, we are referring to freedom, not
23 | price. Our General Public Licenses are designed to make sure that you
24 | have the freedom to distribute copies of free software (and charge for
25 | them if you wish), that you receive source code or can get it if you
26 | want it, that you can change the software or use pieces of it in new
27 | free programs, and that you know you can do these things.
28 |
29 | To protect your rights, we need to prevent others from denying you
30 | these rights or asking you to surrender the rights. Therefore, you have
31 | certain responsibilities if you distribute copies of the software, or if
32 | you modify it: responsibilities to respect the freedom of others.
33 |
34 | For example, if you distribute copies of such a program, whether
35 | gratis or for a fee, you must pass on to the recipients the same
36 | freedoms that you received. You must make sure that they, too, receive
37 | or can get the source code. And you must show them these terms so they
38 | know their rights.
39 |
40 | Developers that use the GNU GPL protect your rights with two steps:
41 | (1) assert copyright on the software, and (2) offer you this License
42 | giving you legal permission to copy, distribute and/or modify it.
43 |
44 | For the developers' and authors' protection, the GPL clearly explains
45 | that there is no warranty for this free software. For both users' and
46 | authors' sake, the GPL requires that modified versions be marked as
47 | changed, so that their problems will not be attributed erroneously to
48 | authors of previous versions.
49 |
50 | Some devices are designed to deny users access to install or run
51 | modified versions of the software inside them, although the manufacturer
52 | can do so. This is fundamentally incompatible with the aim of
53 | protecting users' freedom to change the software. The systematic
54 | pattern of such abuse occurs in the area of products for individuals to
55 | use, which is precisely where it is most unacceptable. Therefore, we
56 | have designed this version of the GPL to prohibit the practice for those
57 | products. If such problems arise substantially in other domains, we
58 | stand ready to extend this provision to those domains in future versions
59 | of the GPL, as needed to protect the freedom of users.
60 |
61 | Finally, every program is threatened constantly by software patents.
62 | States should not allow patents to restrict development and use of
63 | software on general-purpose computers, but in those that do, we wish to
64 | avoid the special danger that patents applied to a free program could
65 | make it effectively proprietary. To prevent this, the GPL assures that
66 | patents cannot be used to render the program non-free.
67 |
68 | The precise terms and conditions for copying, distribution and
69 | modification follow.
70 |
71 | TERMS AND CONDITIONS
72 |
73 | 0. Definitions.
74 |
75 | "This License" refers to version 3 of the GNU General Public License.
76 |
77 | "Copyright" also means copyright-like laws that apply to other kinds of
78 | works, such as semiconductor masks.
79 |
80 | "The Program" refers to any copyrightable work licensed under this
81 | License. Each licensee is addressed as "you". "Licensees" and
82 | "recipients" may be individuals or organizations.
83 |
84 | To "modify" a work means to copy from or adapt all or part of the work
85 | in a fashion requiring copyright permission, other than the making of an
86 | exact copy. The resulting work is called a "modified version" of the
87 | earlier work or a work "based on" the earlier work.
88 |
89 | A "covered work" means either the unmodified Program or a work based
90 | on the Program.
91 |
92 | To "propagate" a work means to do anything with it that, without
93 | permission, would make you directly or secondarily liable for
94 | infringement under applicable copyright law, except executing it on a
95 | computer or modifying a private copy. Propagation includes copying,
96 | distribution (with or without modification), making available to the
97 | public, and in some countries other activities as well.
98 |
99 | To "convey" a work means any kind of propagation that enables other
100 | parties to make or receive copies. Mere interaction with a user through
101 | a computer network, with no transfer of a copy, is not conveying.
102 |
103 | An interactive user interface displays "Appropriate Legal Notices"
104 | to the extent that it includes a convenient and prominently visible
105 | feature that (1) displays an appropriate copyright notice, and (2)
106 | tells the user that there is no warranty for the work (except to the
107 | extent that warranties are provided), that licensees may convey the
108 | work under this License, and how to view a copy of this License. If
109 | the interface presents a list of user commands or options, such as a
110 | menu, a prominent item in the list meets this criterion.
111 |
112 | 1. Source Code.
113 |
114 | The "source code" for a work means the preferred form of the work
115 | for making modifications to it. "Object code" means any non-source
116 | form of a work.
117 |
118 | A "Standard Interface" means an interface that either is an official
119 | standard defined by a recognized standards body, or, in the case of
120 | interfaces specified for a particular programming language, one that
121 | is widely used among developers working in that language.
122 |
123 | The "System Libraries" of an executable work include anything, other
124 | than the work as a whole, that (a) is included in the normal form of
125 | packaging a Major Component, but which is not part of that Major
126 | Component, and (b) serves only to enable use of the work with that
127 | Major Component, or to implement a Standard Interface for which an
128 | implementation is available to the public in source code form. A
129 | "Major Component", in this context, means a major essential component
130 | (kernel, window system, and so on) of the specific operating system
131 | (if any) on which the executable work runs, or a compiler used to
132 | produce the work, or an object code interpreter used to run it.
133 |
134 | The "Corresponding Source" for a work in object code form means all
135 | the source code needed to generate, install, and (for an executable
136 | work) run the object code and to modify the work, including scripts to
137 | control those activities. However, it does not include the work's
138 | System Libraries, or general-purpose tools or generally available free
139 | programs which are used unmodified in performing those activities but
140 | which are not part of the work. For example, Corresponding Source
141 | includes interface definition files associated with source files for
142 | the work, and the source code for shared libraries and dynamically
143 | linked subprograms that the work is specifically designed to require,
144 | such as by intimate data communication or control flow between those
145 | subprograms and other parts of the work.
146 |
147 | The Corresponding Source need not include anything that users
148 | can regenerate automatically from other parts of the Corresponding
149 | Source.
150 |
151 | The Corresponding Source for a work in source code form is that
152 | same work.
153 |
154 | 2. Basic Permissions.
155 |
156 | All rights granted under this License are granted for the term of
157 | copyright on the Program, and are irrevocable provided the stated
158 | conditions are met. This License explicitly affirms your unlimited
159 | permission to run the unmodified Program. The output from running a
160 | covered work is covered by this License only if the output, given its
161 | content, constitutes a covered work. This License acknowledges your
162 | rights of fair use or other equivalent, as provided by copyright law.
163 |
164 | You may make, run and propagate covered works that you do not
165 | convey, without conditions so long as your license otherwise remains
166 | in force. You may convey covered works to others for the sole purpose
167 | of having them make modifications exclusively for you, or provide you
168 | with facilities for running those works, provided that you comply with
169 | the terms of this License in conveying all material for which you do
170 | not control copyright. Those thus making or running the covered works
171 | for you must do so exclusively on your behalf, under your direction
172 | and control, on terms that prohibit them from making any copies of
173 | your copyrighted material outside their relationship with you.
174 |
175 | Conveying under any other circumstances is permitted solely under
176 | the conditions stated below. Sublicensing is not allowed; section 10
177 | makes it unnecessary.
178 |
179 | 3. Protecting Users' Legal Rights From Anti-Circumvention Law.
180 |
181 | No covered work shall be deemed part of an effective technological
182 | measure under any applicable law fulfilling obligations under article
183 | 11 of the WIPO copyright treaty adopted on 20 December 1996, or
184 | similar laws prohibiting or restricting circumvention of such
185 | measures.
186 |
187 | When you convey a covered work, you waive any legal power to forbid
188 | circumvention of technological measures to the extent such circumvention
189 | is effected by exercising rights under this License with respect to
190 | the covered work, and you disclaim any intention to limit operation or
191 | modification of the work as a means of enforcing, against the work's
192 | users, your or third parties' legal rights to forbid circumvention of
193 | technological measures.
194 |
195 | 4. Conveying Verbatim Copies.
196 |
197 | You may convey verbatim copies of the Program's source code as you
198 | receive it, in any medium, provided that you conspicuously and
199 | appropriately publish on each copy an appropriate copyright notice;
200 | keep intact all notices stating that this License and any
201 | non-permissive terms added in accord with section 7 apply to the code;
202 | keep intact all notices of the absence of any warranty; and give all
203 | recipients a copy of this License along with the Program.
204 |
205 | You may charge any price or no price for each copy that you convey,
206 | and you may offer support or warranty protection for a fee.
207 |
208 | 5. Conveying Modified Source Versions.
209 |
210 | You may convey a work based on the Program, or the modifications to
211 | produce it from the Program, in the form of source code under the
212 | terms of section 4, provided that you also meet all of these conditions:
213 |
214 | a) The work must carry prominent notices stating that you modified
215 | it, and giving a relevant date.
216 |
217 | b) The work must carry prominent notices stating that it is
218 | released under this License and any conditions added under section
219 | 7. This requirement modifies the requirement in section 4 to
220 | "keep intact all notices".
221 |
222 | c) You must license the entire work, as a whole, under this
223 | License to anyone who comes into possession of a copy. This
224 | License will therefore apply, along with any applicable section 7
225 | additional terms, to the whole of the work, and all its parts,
226 | regardless of how they are packaged. This License gives no
227 | permission to license the work in any other way, but it does not
228 | invalidate such permission if you have separately received it.
229 |
230 | d) If the work has interactive user interfaces, each must display
231 | Appropriate Legal Notices; however, if the Program has interactive
232 | interfaces that do not display Appropriate Legal Notices, your
233 | work need not make them do so.
234 |
235 | A compilation of a covered work with other separate and independent
236 | works, which are not by their nature extensions of the covered work,
237 | and which are not combined with it such as to form a larger program,
238 | in or on a volume of a storage or distribution medium, is called an
239 | "aggregate" if the compilation and its resulting copyright are not
240 | used to limit the access or legal rights of the compilation's users
241 | beyond what the individual works permit. Inclusion of a covered work
242 | in an aggregate does not cause this License to apply to the other
243 | parts of the aggregate.
244 |
245 | 6. Conveying Non-Source Forms.
246 |
247 | You may convey a covered work in object code form under the terms
248 | of sections 4 and 5, provided that you also convey the
249 | machine-readable Corresponding Source under the terms of this License,
250 | in one of these ways:
251 |
252 | a) Convey the object code in, or embodied in, a physical product
253 | (including a physical distribution medium), accompanied by the
254 | Corresponding Source fixed on a durable physical medium
255 | customarily used for software interchange.
256 |
257 | b) Convey the object code in, or embodied in, a physical product
258 | (including a physical distribution medium), accompanied by a
259 | written offer, valid for at least three years and valid for as
260 | long as you offer spare parts or customer support for that product
261 | model, to give anyone who possesses the object code either (1) a
262 | copy of the Corresponding Source for all the software in the
263 | product that is covered by this License, on a durable physical
264 | medium customarily used for software interchange, for a price no
265 | more than your reasonable cost of physically performing this
266 | conveying of source, or (2) access to copy the
267 | Corresponding Source from a network server at no charge.
268 |
269 | c) Convey individual copies of the object code with a copy of the
270 | written offer to provide the Corresponding Source. This
271 | alternative is allowed only occasionally and noncommercially, and
272 | only if you received the object code with such an offer, in accord
273 | with subsection 6b.
274 |
275 | d) Convey the object code by offering access from a designated
276 | place (gratis or for a charge), and offer equivalent access to the
277 | Corresponding Source in the same way through the same place at no
278 | further charge. You need not require recipients to copy the
279 | Corresponding Source along with the object code. If the place to
280 | copy the object code is a network server, the Corresponding Source
281 | may be on a different server (operated by you or a third party)
282 | that supports equivalent copying facilities, provided you maintain
283 | clear directions next to the object code saying where to find the
284 | Corresponding Source. Regardless of what server hosts the
285 | Corresponding Source, you remain obligated to ensure that it is
286 | available for as long as needed to satisfy these requirements.
287 |
288 | e) Convey the object code using peer-to-peer transmission, provided
289 | you inform other peers where the object code and Corresponding
290 | Source of the work are being offered to the general public at no
291 | charge under subsection 6d.
292 |
293 | A separable portion of the object code, whose source code is excluded
294 | from the Corresponding Source as a System Library, need not be
295 | included in conveying the object code work.
296 |
297 | A "User Product" is either (1) a "consumer product", which means any
298 | tangible personal property which is normally used for personal, family,
299 | or household purposes, or (2) anything designed or sold for incorporation
300 | into a dwelling. In determining whether a product is a consumer product,
301 | doubtful cases shall be resolved in favor of coverage. For a particular
302 | product received by a particular user, "normally used" refers to a
303 | typical or common use of that class of product, regardless of the status
304 | of the particular user or of the way in which the particular user
305 | actually uses, or expects or is expected to use, the product. A product
306 | is a consumer product regardless of whether the product has substantial
307 | commercial, industrial or non-consumer uses, unless such uses represent
308 | the only significant mode of use of the product.
309 |
310 | "Installation Information" for a User Product means any methods,
311 | procedures, authorization keys, or other information required to install
312 | and execute modified versions of a covered work in that User Product from
313 | a modified version of its Corresponding Source. The information must
314 | suffice to ensure that the continued functioning of the modified object
315 | code is in no case prevented or interfered with solely because
316 | modification has been made.
317 |
318 | If you convey an object code work under this section in, or with, or
319 | specifically for use in, a User Product, and the conveying occurs as
320 | part of a transaction in which the right of possession and use of the
321 | User Product is transferred to the recipient in perpetuity or for a
322 | fixed term (regardless of how the transaction is characterized), the
323 | Corresponding Source conveyed under this section must be accompanied
324 | by the Installation Information. But this requirement does not apply
325 | if neither you nor any third party retains the ability to install
326 | modified object code on the User Product (for example, the work has
327 | been installed in ROM).
328 |
329 | The requirement to provide Installation Information does not include a
330 | requirement to continue to provide support service, warranty, or updates
331 | for a work that has been modified or installed by the recipient, or for
332 | the User Product in which it has been modified or installed. Access to a
333 | network may be denied when the modification itself materially and
334 | adversely affects the operation of the network or violates the rules and
335 | protocols for communication across the network.
336 |
337 | Corresponding Source conveyed, and Installation Information provided,
338 | in accord with this section must be in a format that is publicly
339 | documented (and with an implementation available to the public in
340 | source code form), and must require no special password or key for
341 | unpacking, reading or copying.
342 |
343 | 7. Additional Terms.
344 |
345 | "Additional permissions" are terms that supplement the terms of this
346 | License by making exceptions from one or more of its conditions.
347 | Additional permissions that are applicable to the entire Program shall
348 | be treated as though they were included in this License, to the extent
349 | that they are valid under applicable law. If additional permissions
350 | apply only to part of the Program, that part may be used separately
351 | under those permissions, but the entire Program remains governed by
352 | this License without regard to the additional permissions.
353 |
354 | When you convey a copy of a covered work, you may at your option
355 | remove any additional permissions from that copy, or from any part of
356 | it. (Additional permissions may be written to require their own
357 | removal in certain cases when you modify the work.) You may place
358 | additional permissions on material, added by you to a covered work,
359 | for which you have or can give appropriate copyright permission.
360 |
361 | Notwithstanding any other provision of this License, for material you
362 | add to a covered work, you may (if authorized by the copyright holders of
363 | that material) supplement the terms of this License with terms:
364 |
365 | a) Disclaiming warranty or limiting liability differently from the
366 | terms of sections 15 and 16 of this License; or
367 |
368 | b) Requiring preservation of specified reasonable legal notices or
369 | author attributions in that material or in the Appropriate Legal
370 | Notices displayed by works containing it; or
371 |
372 | c) Prohibiting misrepresentation of the origin of that material, or
373 | requiring that modified versions of such material be marked in
374 | reasonable ways as different from the original version; or
375 |
376 | d) Limiting the use for publicity purposes of names of licensors or
377 | authors of the material; or
378 |
379 | e) Declining to grant rights under trademark law for use of some
380 | trade names, trademarks, or service marks; or
381 |
382 | f) Requiring indemnification of licensors and authors of that
383 | material by anyone who conveys the material (or modified versions of
384 | it) with contractual assumptions of liability to the recipient, for
385 | any liability that these contractual assumptions directly impose on
386 | those licensors and authors.
387 |
388 | All other non-permissive additional terms are considered "further
389 | restrictions" within the meaning of section 10. If the Program as you
390 | received it, or any part of it, contains a notice stating that it is
391 | governed by this License along with a term that is a further
392 | restriction, you may remove that term. If a license document contains
393 | a further restriction but permits relicensing or conveying under this
394 | License, you may add to a covered work material governed by the terms
395 | of that license document, provided that the further restriction does
396 | not survive such relicensing or conveying.
397 |
398 | If you add terms to a covered work in accord with this section, you
399 | must place, in the relevant source files, a statement of the
400 | additional terms that apply to those files, or a notice indicating
401 | where to find the applicable terms.
402 |
403 | Additional terms, permissive or non-permissive, may be stated in the
404 | form of a separately written license, or stated as exceptions;
405 | the above requirements apply either way.
406 |
407 | 8. Termination.
408 |
409 | You may not propagate or modify a covered work except as expressly
410 | provided under this License. Any attempt otherwise to propagate or
411 | modify it is void, and will automatically terminate your rights under
412 | this License (including any patent licenses granted under the third
413 | paragraph of section 11).
414 |
415 | However, if you cease all violation of this License, then your
416 | license from a particular copyright holder is reinstated (a)
417 | provisionally, unless and until the copyright holder explicitly and
418 | finally terminates your license, and (b) permanently, if the copyright
419 | holder fails to notify you of the violation by some reasonable means
420 | prior to 60 days after the cessation.
421 |
422 | Moreover, your license from a particular copyright holder is
423 | reinstated permanently if the copyright holder notifies you of the
424 | violation by some reasonable means, this is the first time you have
425 | received notice of violation of this License (for any work) from that
426 | copyright holder, and you cure the violation prior to 30 days after
427 | your receipt of the notice.
428 |
429 | Termination of your rights under this section does not terminate the
430 | licenses of parties who have received copies or rights from you under
431 | this License. If your rights have been terminated and not permanently
432 | reinstated, you do not qualify to receive new licenses for the same
433 | material under section 10.
434 |
435 | 9. Acceptance Not Required for Having Copies.
436 |
437 | You are not required to accept this License in order to receive or
438 | run a copy of the Program. Ancillary propagation of a covered work
439 | occurring solely as a consequence of using peer-to-peer transmission
440 | to receive a copy likewise does not require acceptance. However,
441 | nothing other than this License grants you permission to propagate or
442 | modify any covered work. These actions infringe copyright if you do
443 | not accept this License. Therefore, by modifying or propagating a
444 | covered work, you indicate your acceptance of this License to do so.
445 |
446 | 10. Automatic Licensing of Downstream Recipients.
447 |
448 | Each time you convey a covered work, the recipient automatically
449 | receives a license from the original licensors, to run, modify and
450 | propagate that work, subject to this License. You are not responsible
451 | for enforcing compliance by third parties with this License.
452 |
453 | An "entity transaction" is a transaction transferring control of an
454 | organization, or substantially all assets of one, or subdividing an
455 | organization, or merging organizations. If propagation of a covered
456 | work results from an entity transaction, each party to that
457 | transaction who receives a copy of the work also receives whatever
458 | licenses to the work the party's predecessor in interest had or could
459 | give under the previous paragraph, plus a right to possession of the
460 | Corresponding Source of the work from the predecessor in interest, if
461 | the predecessor has it or can get it with reasonable efforts.
462 |
463 | You may not impose any further restrictions on the exercise of the
464 | rights granted or affirmed under this License. For example, you may
465 | not impose a license fee, royalty, or other charge for exercise of
466 | rights granted under this License, and you may not initiate litigation
467 | (including a cross-claim or counterclaim in a lawsuit) alleging that
468 | any patent claim is infringed by making, using, selling, offering for
469 | sale, or importing the Program or any portion of it.
470 |
471 | 11. Patents.
472 |
473 | A "contributor" is a copyright holder who authorizes use under this
474 | License of the Program or a work on which the Program is based. The
475 | work thus licensed is called the contributor's "contributor version".
476 |
477 | A contributor's "essential patent claims" are all patent claims
478 | owned or controlled by the contributor, whether already acquired or
479 | hereafter acquired, that would be infringed by some manner, permitted
480 | by this License, of making, using, or selling its contributor version,
481 | but do not include claims that would be infringed only as a
482 | consequence of further modification of the contributor version. For
483 | purposes of this definition, "control" includes the right to grant
484 | patent sublicenses in a manner consistent with the requirements of
485 | this License.
486 |
487 | Each contributor grants you a non-exclusive, worldwide, royalty-free
488 | patent license under the contributor's essential patent claims, to
489 | make, use, sell, offer for sale, import and otherwise run, modify and
490 | propagate the contents of its contributor version.
491 |
492 | In the following three paragraphs, a "patent license" is any express
493 | agreement or commitment, however denominated, not to enforce a patent
494 | (such as an express permission to practice a patent or covenant not to
495 | sue for patent infringement). To "grant" such a patent license to a
496 | party means to make such an agreement or commitment not to enforce a
497 | patent against the party.
498 |
499 | If you convey a covered work, knowingly relying on a patent license,
500 | and the Corresponding Source of the work is not available for anyone
501 | to copy, free of charge and under the terms of this License, through a
502 | publicly available network server or other readily accessible means,
503 | then you must either (1) cause the Corresponding Source to be so
504 | available, or (2) arrange to deprive yourself of the benefit of the
505 | patent license for this particular work, or (3) arrange, in a manner
506 | consistent with the requirements of this License, to extend the patent
507 | license to downstream recipients. "Knowingly relying" means you have
508 | actual knowledge that, but for the patent license, your conveying the
509 | covered work in a country, or your recipient's use of the covered work
510 | in a country, would infringe one or more identifiable patents in that
511 | country that you have reason to believe are valid.
512 |
513 | If, pursuant to or in connection with a single transaction or
514 | arrangement, you convey, or propagate by procuring conveyance of, a
515 | covered work, and grant a patent license to some of the parties
516 | receiving the covered work authorizing them to use, propagate, modify
517 | or convey a specific copy of the covered work, then the patent license
518 | you grant is automatically extended to all recipients of the covered
519 | work and works based on it.
520 |
521 | A patent license is "discriminatory" if it does not include within
522 | the scope of its coverage, prohibits the exercise of, or is
523 | conditioned on the non-exercise of one or more of the rights that are
524 | specifically granted under this License. You may not convey a covered
525 | work if you are a party to an arrangement with a third party that is
526 | in the business of distributing software, under which you make payment
527 | to the third party based on the extent of your activity of conveying
528 | the work, and under which the third party grants, to any of the
529 | parties who would receive the covered work from you, a discriminatory
530 | patent license (a) in connection with copies of the covered work
531 | conveyed by you (or copies made from those copies), or (b) primarily
532 | for and in connection with specific products or compilations that
533 | contain the covered work, unless you entered into that arrangement,
534 | or that patent license was granted, prior to 28 March 2007.
535 |
536 | Nothing in this License shall be construed as excluding or limiting
537 | any implied license or other defenses to infringement that may
538 | otherwise be available to you under applicable patent law.
539 |
540 | 12. No Surrender of Others' Freedom.
541 |
542 | If conditions are imposed on you (whether by court order, agreement or
543 | otherwise) that contradict the conditions of this License, they do not
544 | excuse you from the conditions of this License. If you cannot convey a
545 | covered work so as to satisfy simultaneously your obligations under this
546 | License and any other pertinent obligations, then as a consequence you may
547 | not convey it at all. For example, if you agree to terms that obligate you
548 | to collect a royalty for further conveying from those to whom you convey
549 | the Program, the only way you could satisfy both those terms and this
550 | License would be to refrain entirely from conveying the Program.
551 |
552 | 13. Use with the GNU Affero General Public License.
553 |
554 | Notwithstanding any other provision of this License, you have
555 | permission to link or combine any covered work with a work licensed
556 | under version 3 of the GNU Affero General Public License into a single
557 | combined work, and to convey the resulting work. The terms of this
558 | License will continue to apply to the part which is the covered work,
559 | but the special requirements of the GNU Affero General Public License,
560 | section 13, concerning interaction through a network will apply to the
561 | combination as such.
562 |
563 | 14. Revised Versions of this License.
564 |
565 | The Free Software Foundation may publish revised and/or new versions of
566 | the GNU General Public License from time to time. Such new versions will
567 | be similar in spirit to the present version, but may differ in detail to
568 | address new problems or concerns.
569 |
570 | Each version is given a distinguishing version number. If the
571 | Program specifies that a certain numbered version of the GNU General
572 | Public License "or any later version" applies to it, you have the
573 | option of following the terms and conditions either of that numbered
574 | version or of any later version published by the Free Software
575 | Foundation. If the Program does not specify a version number of the
576 | GNU General Public License, you may choose any version ever published
577 | by the Free Software Foundation.
578 |
579 | If the Program specifies that a proxy can decide which future
580 | versions of the GNU General Public License can be used, that proxy's
581 | public statement of acceptance of a version permanently authorizes you
582 | to choose that version for the Program.
583 |
584 | Later license versions may give you additional or different
585 | permissions. However, no additional obligations are imposed on any
586 | author or copyright holder as a result of your choosing to follow a
587 | later version.
588 |
589 | 15. Disclaimer of Warranty.
590 |
591 | THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY
592 | APPLICABLE LAW. EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT
593 | HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY
594 | OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO,
595 | THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
596 | PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM
597 | IS WITH YOU. SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF
598 | ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
599 |
600 | 16. Limitation of Liability.
601 |
602 | IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
603 | WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS
604 | THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY
605 | GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE
606 | USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF
607 | DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD
608 | PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS),
609 | EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF
610 | SUCH DAMAGES.
611 |
612 | 17. Interpretation of Sections 15 and 16.
613 |
614 | If the disclaimer of warranty and limitation of liability provided
615 | above cannot be given local legal effect according to their terms,
616 | reviewing courts shall apply local law that most closely approximates
617 | an absolute waiver of all civil liability in connection with the
618 | Program, unless a warranty or assumption of liability accompanies a
619 | copy of the Program in return for a fee.
620 |
621 | END OF TERMS AND CONDITIONS
622 |
623 | How to Apply These Terms to Your New Programs
624 |
625 | If you develop a new program, and you want it to be of the greatest
626 | possible use to the public, the best way to achieve this is to make it
627 | free software which everyone can redistribute and change under these terms.
628 |
629 | To do so, attach the following notices to the program. It is safest
630 | to attach them to the start of each source file to most effectively
631 | state the exclusion of warranty; and each file should have at least
632 | the "copyright" line and a pointer to where the full notice is found.
633 |
634 | {one line to give the program's name and a brief idea of what it does.}
635 | Copyright (C) {year} {name of author}
636 |
637 | This program is free software: you can redistribute it and/or modify
638 | it under the terms of the GNU General Public License as published by
639 | the Free Software Foundation, either version 3 of the License, or
640 | (at your option) any later version.
641 |
642 | This program is distributed in the hope that it will be useful,
643 | but WITHOUT ANY WARRANTY; without even the implied warranty of
644 | MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
645 | GNU General Public License for more details.
646 |
647 | You should have received a copy of the GNU General Public License
648 | along with this program. If not, see .
649 |
650 | Also add information on how to contact you by electronic and paper mail.
651 |
652 | If the program does terminal interaction, make it output a short
653 | notice like this when it starts in an interactive mode:
654 |
655 | {project} Copyright (C) {year} {fullname}
656 | This program comes with ABSOLUTELY NO WARRANTY; for details type `show w'.
657 | This is free software, and you are welcome to redistribute it
658 | under certain conditions; type `show c' for details.
659 |
660 | The hypothetical commands `show w' and `show c' should show the appropriate
661 | parts of the General Public License. Of course, your program's commands
662 | might be different; for a GUI interface, you would use an "about box".
663 |
664 | You should also get your employer (if you work as a programmer) or school,
665 | if any, to sign a "copyright disclaimer" for the program, if necessary.
666 | For more information on this, and how to apply and follow the GNU GPL, see
667 | .
668 |
669 | The GNU General Public License does not permit incorporating your program
670 | into proprietary programs. If your program is a subroutine library, you
671 | may consider it more useful to permit linking proprietary applications with
672 | the library. If this is what you want to do, use the GNU Lesser General
673 | Public License instead of this License. But first, please read
674 | .
675 |
--------------------------------------------------------------------------------
14 | 
15 |