diff options
| author | Antoni Oliver <aoliverg@uoc.edu> | 2020-10-06 18:32:12 +0300 |
|---|---|---|
| committer | Antoni Oliver <aoliverg@uoc.edu> | 2020-10-06 18:32:12 +0300 |
| commit | 783b6fb789242ec5394ccf018b931d3e41abfe52 (patch) | |
| tree | bf316dc1f532d851c409813269675413b8aab8b4 | |
First commit.
| -rwxr-xr-x | TBXTools.py | 2367 | ||||
| -rw-r--r-- | gpl-3.0.txt | 674 |
2 files changed, 3041 insertions, 0 deletions
diff --git a/TBXTools.py b/TBXTools.py new file mode 100755 index 0000000..80c2075 --- /dev/null +++ b/TBXTools.py @@ -0,0 +1,2367 @@ +import os +import codecs +import sqlite3 +import xml.etree.cElementTree as etree + +import nltk +from nltk.util import ngrams +from nltk.probability import FreqDist +from nltk.collocations import * +import re +import pickle +import gzip +import operator +import sys +import math + +import string + +#version: 2020/10/06 +#Copyright: Antoni Oliver (2020) - Universitat Oberta de Catalunya - aoliverg@uoc.edu +# This program is free software: you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation, either version 3 of the License, or +# (at your option) any later version. + +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. + +# You should have received a copy of the GNU General Public License +# along with this program. If not, see <https://www.gnu.org/licenses/>. + + +class TBXTools: + '''Class for automatic terminology extraction and terminology management.''' + def __init__(self): + self.maxinserts=10000 #controls the maximum number of inserts in memory + self.sl_lang="" + self.tl_lang="" + self.max_id_corpus=0 + + self.sl_stopwords=[] + self.tl_stopwords=[] + self.sl_inner_stopwords=[] + self.tl_inner_stopwords=[] + self.sl_exclsions_regexps=[] + self.tl_exclusion_regexps=[] + self.sl_morphonorm_rules=[] + self.tl_morphonorm_rules=[] + self.evaluation_terms={} + self.exclusion_terms={} + self.exclusion_no_terms={} + self.ngrams={} + self.tagged_ngrams={} + self.term_candidates={} + self.linguistic_patterns={} + + self.knownterms=[] + self.n_min=1 + self.n_max=5 + + self.punctuation=string.punctuation + self.sl_stopwords.extend(self.punctuation) + self.tl_stopwords.extend(self.punctuation) + self.sl_inner_stopwords.extend(self.punctuation) + self.tl_inner_stopwords.extend(self.punctuation) + + #FREELING API + self.FREELINGDIR = "/usr/local"; + self.DATA = self.FREELINGDIR+"/share/freeling/"; + + def create_project(self,project_name,sl_lang,tl_lang="null",overwrite=False): + '''Opens a project. If the project already exists, it raises an exception. To avoid the exception use overwrite=True. To open existing projects, use the open_project method.''' + if os.path.isfile(project_name) and not overwrite: + raise Exception("This file already exists") + + else: + if os.path.isfile(project_name) and overwrite: + os.remove(project_name) + self.sl_lang=sl_lang + self.tl_lang=tl_lang + self.conn=sqlite3.connect(project_name) + self.cur = self.conn.cursor() + self.cur2 = self.conn.cursor() + with self.conn: + self.cur = self.conn.cursor() + self.cur.execute("CREATE TABLE configuration(id INTEGER PRIMARY KEY, sl_lang TEXT, tl_lang TEXT)") + self.cur.execute("CREATE TABLE sl_corpus(id INTEGER PRIMARY KEY, segment TEXT)") + self.cur.execute("CREATE TABLE tl_corpus(id INTEGER PRIMARY KEY, segment TEXT)") + self.cur.execute("CREATE TABLE sl_tagged_corpus(id INTEGER PRIMARY KEY, tagged_segment TEXT)") + self.cur.execute("CREATE TABLE tl_tagged_corpus(id INTEGER PRIMARY KEY, tagged_segment TEXT)") + self.cur.execute("CREATE TABLE sl_stopwords (id INTEGER PRIMARY KEY AUTOINCREMENT, sl_stopword TEXT)") + self.cur.execute("CREATE TABLE sl_inner_stopwords (id INTEGER PRIMARY KEY AUTOINCREMENT, sl_inner_stopword TEXT)") + self.cur.execute("CREATE TABLE tl_stopwords (id INTEGER PRIMARY KEY AUTOINCREMENT, tl_stopword TEXT)") + self.cur.execute("CREATE TABLE tl_inner_stopwords (id INTEGER PRIMARY KEY AUTOINCREMENT, tl_inner_stopword TEXT)") + self.cur.execute("CREATE TABLE sl_exclusion_regexps (id INTEGER PRIMARY KEY AUTOINCREMENT, sl_exclusion_regexp TEXT)") + self.cur.execute("CREATE TABLE tl_exclusion_regexps (id INTEGER PRIMARY KEY AUTOINCREMENT, tl_exclusion_regexp TEXT)") + self.cur.execute("CREATE TABLE sl_morphonorm_rules (id INTEGER PRIMARY KEY AUTOINCREMENT, sl_morphonorm_rule TEXT)") + self.cur.execute("CREATE TABLE tl_morphonorm_rules (id INTEGER PRIMARY KEY AUTOINCREMENT, tl_morphonorm_rule TEXT)") + #self.cur.execute("CREATE TABLE sl_patterns (id INTEGER PRIMARY KEY AUTOINCREMENT, sl_pattern TEXT)") + #self.cur.execute("CREATE TABLE tl_patterns (id INTEGER PRIMARY KEY AUTOINCREMENT, tl_pattern TEXT)") + self.cur.execute("CREATE TABLE evaluation_terms (id INTEGER PRIMARY KEY AUTOINCREMENT, sl_term TEXT, tl_term TEXT)") + self.cur.execute("CREATE TABLE exclusion_terms (id INTEGER PRIMARY KEY AUTOINCREMENT, sl_term TEXT, tl_term TEXT)") + self.cur.execute("CREATE TABLE exclusion_noterms (id INTEGER PRIMARY KEY AUTOINCREMENT, sl_term TEXT, tl_term TEXT)") + self.cur.execute("CREATE TABLE tokens (id INTEGER PRIMARY KEY AUTOINCREMENT, token TEXT, frequency INTEGER)") + self.cur.execute("CREATE TABLE ngrams (id INTEGER PRIMARY KEY AUTOINCREMENT, ngram TEXT, n INTEGER, frequency INTEGER)") + self.cur.execute("CREATE TABLE tagged_ngrams (id INTEGER PRIMARY KEY AUTOINCREMENT, ngram TEXT, tagged_ngram TEXT, n INTEGER, frequency INTEGER)") + + self.cur.execute("CREATE INDEX indextaggedngram on tagged_ngrams (ngram);") + + + self.cur.execute("CREATE TABLE term_candidates (id INTEGER PRIMARY KEY AUTOINCREMENT, candidate TEXT, n INTEGER, frequency INTEGER, measure TEXT, value FLOAT)") + self.cur.execute("CREATE TABLE index_pt(id INTEGER PRIMARY KEY AUTOINCREMENT, source TEXT, target TEXT, probability FLOAT)") + self.cur.execute("CREATE INDEX index_index_pt on index_pt (source);") + self.cur.execute("CREATE TABLE linguistic_patterns (id INTEGER PRIMARY KEY AUTOINCREMENT, linguistic_pattern TEXT)") + + self.cur.execute("INSERT INTO configuration (id, sl_lang, tl_lang) VALUES (?,?,?)",[0,self.sl_lang,self.tl_lang]) + self.conn.commit() + + def open_project(self,project_name): + '''Opens an existing project. If the project doesn't exist it raises an exception.''' + if not os.path.isfile(project_name): + raise Exception("Project not found") + else: + self.conn=sqlite3.connect(project_name) + self.cur = self.conn.cursor() + self.cur2 = self.conn.cursor() + self.maxsc=0 + self.maxtc=0 + with self.conn: + self.cur.execute('SELECT sl_lang from configuration where id=0') + self.sl_lang=self.cur.fetchone()[0] + self.cur.execute('SELECT tl_lang from configuration where id=0') + self.tl_lang=self.cur.fetchone()[0] + #Maximum position in corpora + self.maxpositions=[] + self.cur.execute('SELECT max(id) from sl_corpus') + self.qresult=self.cur.fetchone()[0] + if not self.qresult==None: + self.maxpositions.append(self.qresult) + else: + self.maxpositions.append(0) + self.cur.execute('SELECT max(id) from tl_corpus') + self.qresult=self.cur.fetchone()[0] + if not self.qresult==None: + self.maxpositions.append(self.qresult) + else: + self.maxpositions.append(0) + self.cur.execute('SELECT max(id) from sl_tagged_corpus') + self.qresult=self.cur.fetchone()[0] + if not self.qresult==None: + self.maxpositions.append(self.qresult) + else: + self.maxpositions.append(0) + self.cur.execute('SELECT max(id) from tl_tagged_corpus') + self.qresult=self.cur.fetchone()[0] + if not self.qresult==None: + self.maxpositions.append(self.qresult) + else: + self.maxpositions.append(0) + self.max_id_corpus=max(self.maxpositions) + + + #loading of stopwords + self.cur.execute('SELECT sl_stopword from sl_stopwords') + self.data=self.cur.fetchall() + for self.d in self.data: + self.sl_stopwords.append(self.d[0]) + + self.cur.execute('SELECT tl_stopword from tl_stopwords') + self.data=self.cur.fetchall() + for self.d in self.data: + self.tl_stopwords.append(self.d[0]) + + self.cur.execute('SELECT sl_inner_stopword from sl_inner_stopwords') + self.data=self.cur.fetchall() + for self.d in self.data: + self.sl_inner_stopwords.append(self.d[0]) + + self.cur.execute('SELECT tl_inner_stopword from tl_inner_stopwords') + self.data=self.cur.fetchall() + for self.d in self.data: + self.tl_inner_stopwords.append(self.d[0]) + + self.cur.execute('SELECT sl_exclusion_regexp from sl_exclusion_regexps') + self.data=self.cur.fetchall() + for self.d in self.data: + self.sl_exclusion_regexps.append(self.d[0]) + + self.cur.execute('SELECT tl_exclusion_regexp from tl_exclusion_regexps') + self.data=self.cur.fetchall() + for self.d in self.data: + self.tl_exclusion_regexps.append(self.d[0]) + + self.cur.execute('SELECT sl_morphonorm_rule from sl_morphonorm_rules') + self.data=self.cur.fetchall() + for self.d in self.data: + self.sl_morphonorm_rules.append(self.d[0]) + + self.cur.execute('SELECT tl_morphonorm_rule from tl_morphonorm_rules') + self.data=self.cur.fetchall() + for self.d in self.data: + self.tl_morphonorm_rules.append(self.d[0]) + + self.cur.execute('SELECT sl_term,tl_term from evaluation_terms') + self.data=self.cur.fetchall() + for self.d in self.data: + self.evaluation_terms[self.d[0]]=self.d[1] + + + #METODES DELETES + def delete_sl_corpus(self): + '''Deletes de source language corpus.''' + with self.conn: + self.cur.execute('DELETE FROM sl_corpus') + self.conn.commit() + + def delete_tl_corpus(self): + '''Deletes de target language corpus.''' + with self.conn: + self.cur.execute('DELETE FROM tl_corpus') + self.conn.commit() + + def delete_sl_tagged_corpus(self): + '''Deletes the source language tagged corpus.''' + with self.conn: + self.cur.execute('DELETE FROM sl_tagged_corpus') + self.conn.commit() + + def delete_tl_tagged_corpus(self): + '''Deletes the target language tagged corpu.''' + with self.conn: + self.cur.execute('DELETE FROM tl_tagged_corpus') + self.conn.commit() + + def delete_sl_stopwords(self): + '''Deletes the stop-words for the source language.''' + self.sl_stopwords=[] + with self.conn: + self.cur.execute('DELETE FROM sl_stopwords') + self.conn.commit() + + def delete_tl_stopwords(self): + '''Deletes the stop-words fot the target language.''' + self.tl_stopwords=[] + with self.conn: + self.cur.execute('DELETE FROM tl_stopwords') + self.conn.commit() + + def delete_sl_inner_stopwords(self): + '''Deletes the inner stop-words for the source language.''' + self.sl_inner_stopwords=[] + with self.conn: + self.cur.execute('DELETE FROM sl_inner_stopwords') + self.conn.commit() + + def delete_tl_inner_stopwords(self): + '''Deletes the innter stop-words for the target language.''' + self.tl_inner_stopwords=[] + with self.conn: + self.cur.execute('DELETE FROM tl_inner_stopwords') + self.conn.commit() + + def delete_sl_exclusion_regexps(self): + '''Deletes the exclusion regular expressions for the source language.''' + self.sl_exclusion_regexps=[] + with self.conn: + self.cur.execute('DELETE FROM sl_exclusion_regexps') + self.conn.commit() + + def delete_tl_exclusion_regexps(self): + '''Deletes the exclusion regular expressions for the target language.''' + self.tl_exclusion_regexps=[] + with self.conn: + self.cur.execute('DELETE FROM tl_exclusion_regexps') + self.conn.commit() + + def delete_sl_morphonorm_rules(self): + '''Deletes the morphological normalisation rules for the source language.''' + self.sl_morphonorm_rules=[] + with self.conn: + self.cur.execute('DELETE FROM sl_morphonorm_rules') + self.conn.commit() + + def delete_tl_morphonorm_rules(self): + '''Deletes the morphological normalisation rules for the target language.''' + self.tl_morphonorm_rules=[] + with self.conn: + self.cur.execute('DELETE FROM tl_morphonorm_rules') + self.conn.commit() + + def delete_evaluation_terms(self): + '''Deletes the evaluation terms.''' + self.evaluation_terms={} + with self.conn: + self.cur.execute('DELETE FROM evaluation_terms') + self.conn.commit() + + def delete_exclusion_terms(self): + '''Deletes the exclusion terms.''' + self.exclusion_terms={} + with self.conn: + self.cur.execute('DELETE FROM exclusion_terms') + self.conn.commit() + + def delete_exclusion_no_terms(self): + '''Deletes the exclusion no terms.''' + self.exclusion_terms={} + with self.conn: + self.cur.execute('DELETE FROM exclusion_terms') + self.conn.commit() + + def delete_linguistic_patterns(self): + '''Deletes the linguistic patterns for linguistic terminology extraction.''' + self.exclusion_terms={} + with self.conn: + self.cur.execute('DELETE FROM exclusion_terms') + self.conn.commit() + + def delete_tokens(self): + '''Deletes the tokens,''' + self.ngrams={} + with self.conn: + self.cur.execute('DELETE FROM tokens') + self.conn.commit() + + def delete_ngrams(self): + '''Deletes the ngrams.''' + self.ngrams={} + with self.conn: + self.cur.execute('DELETE FROM ngrams') + self.conn.commit() + + def delete_tagged_ngrams(self): + '''Deletes the tagged ngrams.''' + self.tagged_ngrams={} + with self.conn: + self.cur.execute('DELETE FROM tagged_ngrams') + self.conn.commit() + + def delete_term_candidates(self): + '''Deletes the term candidates.''' + self.term_candidates={} + with self.conn: + self.cur.execute('DELETE FROM term_candidates') + self.conn.commit() + + + def load_sl_corpus(self,corpusfile, encoding="utf-8"): + '''Loads a monolingual corpus for the source language. It's recommended, but not compulsory, that the corpus is segmented (one segment per line). Use TBXTools external tools to segment the corpus. A plain text corpus (not segmented), can be aslo used.''' + self.cf=codecs.open(corpusfile,"r",encoding=encoding,errors="ignore") + self.data=[] + self.continserts=0 + for self.line in self.cf: + + self.continserts+=1 + self.max_id_corpus+=1 + self.record=[] + self.line=self.line.rstrip() + self.record.append(self.max_id_corpus) + self.record.append(self.line) + self.data.append(self.record) + if self.continserts==self.maxinserts: + self.cur.executemany("INSERT INTO sl_corpus (id, segment) VALUES (?,?)",self.data) + self.data=[] + self.continserts=0 + with self.conn: + self.cur.executemany("INSERT INTO sl_corpus (id, segment) VALUES (?,?)",self.data) + self.conn.commit() + + def load_sl_tl_corpus(self,slcorpusfile, tlcorpusfile, encoding="utf-8"): + '''Loads a bilingual corpus in Moses format (that is, in two independent files. It expects one segment per line.''' + self.slcf=codecs.open(slcorpusfile,"r",encoding=encoding) + self.tlcf=codecs.open(tlcorpusfile,"r",encoding=encoding) + self.sl_data=[] + self.tl_data=[] + self.continserts=0 + while 1: + self.sl_segment=self.slcf.readline() + if not self.sl_segment: + break + self.tl_segment=self.tlcf.readline() + self.continserts+=1 + self.max_id_corpus+=1 + self.sl_record=[] + self.tl_record=[] + self.sl_segment=self.sl_segment.rstrip() + self.tl_segment=self.tl_segment.rstrip() + + self.sl_record.append(self.max_id_corpus) + self.tl_record.append(self.max_id_corpus) + self.sl_record.append(self.sl_segment) + self.tl_record.append(self.tl_segment) + self.sl_data.append(self.sl_record) + self.tl_data.append(self.tl_record) + if self.continserts==self.maxinserts: + self.cur.executemany("INSERT INTO sl_corpus (id, segment) VALUES (?,?)",self.sl_data) + self.cur.executemany("INSERT INTO tl_corpus (id, segment) VALUES (?,?)",self.tl_data) + self.sl_data=[] + self.tl_data=[] + self.continserts=0 + with self.conn: + self.cur.executemany("INSERT INTO sl_corpus (id, segment) VALUES (?,?)",self.sl_data) + self.cur.executemany("INSERT INTO tl_corpus (id, segment) VALUES (?,?)",self.tl_data) + self.conn.commit() + + def load_tmx(self,tmx_file, sl_code=None, tl_code= None): + '''Loads a parallel corpus from a TMX file. Source and target language codes should be given. The codes must be the exactly the same as in the TMX file. In no codes are provided, the codes used in the TBXTools project will be used.''' + self.continserts=0 + if sl_code==None: + self.sl_code=self.sl_lang + else: + self.sl_code=sl_code + if tl_code==None: + self.tl_code=self.tl_lang + else: + self.tl_code=tl_code + self.data1=[] + self.data2=[] + self.sl_segment="" + self.tl_segment="" + self.current_lang="" + for self.event, self.elem in etree.iterparse(tmx_file,events=("start","end")): + if self.event=='start': + if self.elem.tag=="tu" and not self.sl_segment=="" and not self.tl_segment=="": + self.continserts+=1 + self.max_id_corpus+=1 + self.record1=[] + self.record2=[] + self.record1.append(self.max_id_corpus) + self.record1.append(self.sl_segment) + self.data1.append(self.record1) + + self.record2.append(self.max_id_corpus) + self.record2.append(self.tl_segment) + self.data2.append(self.record2) + self.sl_segment="" + self.tl_segment="" + if self.continserts==self.maxinserts: + self.cur.executemany("INSERT INTO sl_corpus (id, segment) VALUES (?,?)",self.data1) + self.cur.executemany("INSERT INTO tl_corpus (id, segment) VALUES (?,?)",self.data2) + self.data1=[] + self.data2=[] + self.continserts=0 + self.conn.commit() + elif self.elem.tag=="tuv": + self.current_lang=self.elem.attrib['{http://www.w3.org/XML/1998/namespace}lang'] + elif self.elem.tag=="seg": + if self.elem.text: + self.segmentext=self.elem.text + else: + self.segmentext="" + if self.current_lang==sl_code: + self.sl_segment=self.segmentext + if self.current_lang==tl_code: + self.tl_segment=self.segmentext + + + def load_sl_tagged_corpus(self,corpusfile,format="TBXTools",encoding="utf-8"): + '''Loads the source language tagged corpus. 3 formats are allowed: + - TBXTools: The internal format used by TBXTools. One tagged segment per line. + f1|l1|t1|p1 f2|l2|t2|p2 ... fn|ln|tn|pn + - Freeling: One token per line and segments separated by blank lines + f1 l1 t1 p1 + f2 l2 t2 p2 + ... + fn ln tn pn + - Conll: One of the output formats guiven by the Standford Core NLP analyzer. On token per line and segments separated by blank lines + id1 f1 l1 t1 ... + id2 f2 l2 t2 ... + ... + idn fn ln tn ... + ''' + self.validformarts=["TBXTools","freeling","conll"] + #TODO: Raise exception if not a valid format. + self.cf=codecs.open(corpusfile,"r",encoding=encoding) + if format=="TBXTools": + + self.data=[] + self.continserts=0 + for self.line in self.cf: + self.continserts+=1 + self.max_id_corpus+=1 + self.record=[] + self.line=self.line.rstrip() + self.record.append(self.max_id_corpus) + self.record.append(self.line) + self.data.append(self.record) + if self.continserts==self.maxinserts: + self.cur.executemany("INSERT INTO sl_tagged_corpus (id, tagged_segment) VALUES (?,?)",self.data) + self.data=[] + self.continserts=0 + + with self.conn: + self.cur.executemany("INSERT INTO sl_tagged_corpus (id, tagged_segment) VALUES (?,?)",self.data) + self.conn.commit() + elif format=="freeling": + self.data=[] + self.continserts=0 + self.segment=[] + for self.line in self.cf: + self.line=self.line.rstrip() + if self.line=="": + self.continserts+=1 + self.max_id_corpus+=1 + self.record=[] + self.record.append(self.max_id_corpus) + self.record.append(" ".join(self.segment)) + print(" ".join(self.segment)) + self.data.append(self.record) + if self.continserts==self.maxinserts: + self.cur.executemany("INSERT INTO sl_tagged_corpus (id, tagged_segment) VALUES (?,?)",self.data) + self.data=[] + self.continserts=0 + self.data=[] + self.conn.commit() + self.segment=[] + + else: + self.camps=self.line.split(" ") + self.token=self.camps[0]+"|"+self.camps[1]+"|"+self.camps[2] + + self.segment.append(self.token) + with self.conn: + self.cur.executemany("INSERT INTO sl_tagged_corpus (id, tagged_segment) VALUES (?,?)",self.data) + self.conn.commit() + + + + elif format=="conll": + self.data=[] + self.continserts=0 + self.segment=[] + for self.line in self.cf: + self.line=self.line.rstrip() + if self.line=="": + self.continserts+=1 + self.max_id_corpus+=1 + self.record=[] + self.record.append(self.max_id_corpus) + self.record.append(" ".join(self.segment)) + self.data.append(self.record) + if self.continserts==self.maxinserts: + self.cur.executemany("INSERT INTO sl_tagged_corpus (id, tagged_segment) VALUES (?,?)",self.data) + self.data=[] + self.continserts=0 + self.data=[] + self.conn.commit() + self.segment=[] + + else: + self.camps=self.line.split("\t") + self.token=self.camps[1]+"|"+self.camps[2]+"|"+self.camps[3] + self.segment.append(self.token) + + + + with self.conn: + self.cur.executemany("INSERT INTO sl_tagged_corpus (id, tagged_segment) VALUES (?,?)",self.data) + self.conn.commit() + + + + + + def load_sl_stopwords(self,fitxer,encoding="utf-8"): + '''Loads the stopwords for the source language.''' + self.fc=codecs.open(fitxer,"r",encoding) + self.data=[] + self.record=[] + while 1: + self.linia=self.fc.readline() + if not self.linia: + break + self.linia=self.linia.rstrip() + self.sl_stopwords.append(self.linia) + self.record.append(self.linia) + self.data.append(self.record) + self.record=[] + + for self.punct in self.punctuation: + self.record.append(self.punct) + self.data.append(self.record) + self.record=[] + with self.conn: + self.cur.executemany("INSERT INTO sl_stopwords (sl_stopword) VALUES (?)",self.data) + + def load_tl_stopwords(self,fitxer,encoding="utf-8"): + '''Loads the stopwords for the target language.''' + self.fc=codecs.open(fitxer,"r",encoding) + self.data=[] + self.record=[] + while 1: + self.linia=self.fc.readline() + if not self.linia: + break + self.linia=self.linia.rstrip() + self.tl_stopwords.append(self.linia) + self.record.append(self.linia) + self.data.append(self.record) + self.record=[] + + for self.punct in self.punctuation: + self.record.append(self.punct) + self.data.append(self.record) + self.record=[] + with self.conn: + self.cur.executemany("INSERT INTO tl_stopwords (tl_stopword) VALUES (?)",self.data) + + def load_sl_inner_stopwords(self,fitxer,encoding="utf-8"): + '''Loads the stopwords for the source language.''' + self.fc=codecs.open(fitxer,"r",encoding) + self.data=[] + self.record=[] + while 1: + self.linia=self.fc.readline() + if not self.linia: + break + self.linia=self.linia.rstrip() + self.sl_inner_stopwords.append(self.linia) + self.record.append(self.linia) + self.data.append(self.record) + self.record=[] + + for self.punct in self.punctuation: + self.record.append(self.punct) + self.data.append(self.record) + self.record=[] + with self.conn: + self.cur.executemany("INSERT INTO sl_inner_stopwords (sl_inner_stopword) VALUES (?)",self.data) + + def load_tl_inner_stopwords(self,fitxer,encoding="utf-8"): + '''Loads the inner stopwords for the target language.''' + self.fc=codecs.open(fitxer,"r",encoding) + self.data=[] + self.record=[] + while 1: + self.linia=self.fc.readline() + if not self.linia: + break + self.linia=self.linia.rstrip() + self.tl_inner_stopwords.append(self.linia) + self.record.append(self.linia) + self.data.append(self.record) + self.record=[] + + for self.punct in self.punctuation: + self.record.append(self.punct) + self.data.append(self.record) + self.record=[] + with self.conn: + self.cur.executemany("INSERT INTO tl_inner_stopwords (tl_inner_stopword) VALUES (?)",self.data) + + def load_evaluation_terms(self,arxiu,encoding="utf-8",nmin=0,nmax=1000): + '''Loads the evaluation terms from a tabulated text''' + #TODO Load from TBX + + self.cf=codecs.open(arxiu,"r",encoding=encoding) + self.data=[] + self.continserts=0 + for self.line in self.cf: + + self.line=self.line.rstrip() + self.continserts+=1 + self.record=[] + self.line=self.line.rstrip() + self.camps=self.line.split("\t") + if len(self.camps)==1: + if len(self.camps[0].split(" "))>=nmin and len(self.camps[0].split(" "))<=nmax: + + self.record.append(self.camps[0]) + self.record.append("_") + self.evaluation_terms[self.camps[0]]="_" + self.data.append(self.record) + elif len(self.camps)>1: + if len(self.camps[0].split(" "))>=nmin and len(self.camps[0].split(" "))<=nmax: + self.record.append(self.camps[0]) + self.record.append(self.camps[1]) + self.evaluation_terms[self.camps[0]]=self.camps[1] + self.data.append(self.record) + if self.continserts==self.maxinserts: + + self.cur.executemany("INSERT INTO evaluation_terms (sl_term,tl_term) VALUES (?,?)",self.data) + self.data=[] + self.continserts=0 + with self.conn: + self.cur.executemany("INSERT INTO evaluation_terms (sl_term,tl_term) VALUES (?,?)",self.data) + + self.conn.commit() + + def load_exclusion_terms(self,arxiu,encoding="utf-8",nmin=0,nmax=1000): + '''Loads the exclusion terms from a tabulated text. The terms in the exclusion terms will be deleted from the term candidates. It is useful to store already known terms, and/or term candidates already evaluated either as correct or as incorrect.''' + self.cf=codecs.open(arxiu,"r",encoding=encoding) + self.data=[] + self.continserts=0 + for self.line in self.cf: + self.line=self.line.rstrip() + self.continserts+=1 + self.record=[] + self.line=self.line.rstrip() + self.camps=self.line.split("\t") + if len(self.camps)==1: + self.record.append(self.camps[0]) + self.record.append("_") + self.evaluation_terms[self.camps[0]]="_" + elif len(self.camps)>1: + self.record.append(self.camps[0]) + self.record.append(self.camps[1]) + self.evaluation_terms[self.camps[0]]=self.camps[1] + self.data.append(self.record) + if self.continserts==self.maxinserts: + self.cur.executemany("INSERT INTO exclusion_terms (sl_term,tl_term) VALUES (?,?)",self.data) + self.data=[] + self.continserts=0 + with self.conn: + self.cur.executemany("INSERT INTO exclusion_terms (sl_term,tl_term) VALUES (?,?)",self.data) + + self.conn.commit() + + def load_sl_exclusion_regexps(self,arxiu,encoding="utf-8"): + '''Loads the exclusionregular expressions for the source language.''' + self.cf=codecs.open(arxiu,"r",encoding=encoding) + self.data=[] + for self.line in self.cf: + self.line=self.line.rstrip() + self.record=[] + self.record.append(self.line) + self.data.append(self.record) + + with self.conn: + self.cur.executemany('INSERT INTO sl_exclusion_regexps (sl_exclusion_regexp) VALUES (?)',self.data) + + def load_tl_exclusion_regexps(self,arxiu,encoding="utf-8"): + '''Loads the exclusionregular expressions for the target language.''' + self.cf=codecs.open(arxiu,"r",encoding=encoding) + self.data=[] + for self.line in self.cf: + self.line=self.line.rstrip() + self.record=[] + self.record.append(self.line) + self.data.append(self.record) + + with self.conn: + self.cur.executemany('INSERT INTO tl_exclusion_regexps (sl_exclusion_regexp) VALUES (?)',self.data) + + + def show_term_candidates(self,limit=-1,minfreq=2, minmeasure=-1, show_frequency=True, show_measure=False, mark_eval=False, verbose=False): + '''Shows in screen the term candidates.''' + self.measure=0 + + with self.conn: + self.cur.execute("SELECT sl_term FROM exclusion_terms") + for self.s in self.cur.fetchall(): + self.knownterms.append(self.s[0]) + with self.conn: + self.cur.execute("SELECT frequency,measure,n,candidate FROM term_candidates order by frequency desc limit "+str(limit)) + for self.s in self.cur.fetchall(): + self.frequency=self.s[0] + if self.s[1]==None: + self.measure==0 + else: + self.measure=self.s[1] + self.n=self.s[2] + self.candidate=self.s[3] + if self.n>=self.n_min and self.n<=self.n_max and not self.candidate in self.knownterms: + if mark_eval: + if self.candidate in self.evaluation_terms: + self.candidate="*"+self.candidate + if show_frequency: + self.cadena=str(self.frequency)+"\t"+self.candidate + else: + self.cadena=self.candidate + print(self.cadena) + + def select_unigrams(self,file,position=-1,verbose=True): + sunigrams=codecs.open(file,"w",encoding="utf-8") + self.unigrams={} + self.cur.execute("SELECT frequency,candidate FROM term_candidates order by value desc, frequency desc, random()") + #self.cur.execute("SELECT frequency,value,n,candidate FROM term_candidates order by n desc limit "+str(limit)) + for self.s in self.cur.fetchall(): + self.frequency=self.s[0] + self.candidate=self.s[1].split(" ")[position] + if self.candidate in self.unigrams: + self.unigrams[self.candidate]+=self.frequency + else: + self.unigrams[self.candidate]=self.frequency + #for self.candidate in self.unigrams: + # print(self.unigrams[self.candidate],self.candidate) + + for self.candidate in sorted(self.unigrams, key=self.unigrams.get, reverse=True): + if verbose: + cadena=str(self.unigrams[self.candidate])+"\t"+self.candidate + print(cadena) + sunigrams.write(cadena+"\n") + + + def save_term_candidates(self,outfile,limit=-1,minfreq=2, minmeasure=-1, show_frequency=True, show_measure=False, mark_eval=False, verbose=False): + '''Saves the term candidates in a file.''' + self.sortida=codecs.open(outfile,"w",encoding="utf-8") + self.measure=0 + self.knownterms=[] + with self.conn: + self.cur.execute("SELECT sl_term FROM exclusion_terms") + for self.s in self.cur.fetchall(): + self.knownterms.append(self.s[0]) + with self.conn: + self.cur.execute("SELECT frequency,value,n,candidate FROM term_candidates order by value desc, frequency desc, random() limit "+str(limit)) + #self.cur.execute("SELECT frequency,value,n,candidate FROM term_candidates order by n desc limit "+str(limit)) + for self.s in self.cur.fetchall(): + self.frequency=self.s[0] + if self.s[1]==None: + self.measure==0 + else: + self.measure=self.s[1] + self.n=self.s[2] + self.candidate=self.s[3] + if self.n>=self.n_min and self.n<=self.n_max and not self.candidate in self.knownterms: + if mark_eval: + if self.candidate in self.evaluation_terms: + self.candidate="*"+self.candidate + if show_measure and not show_frequency: + self.cadena=str(self.measure)+"\t"+self.candidate + elif show_frequency and not show_measure: + self.cadena=str(self.frequency)+"\t"+self.candidate + elif show_frequency and show_measure: + self.cadena=str(self.frequency)+"\t"+str(self.measure)+"\t"+self.candidate + else: + self.cadena=self.candidate + if verbose: + print(self.cadena) + self.sortida.write(self.cadena+"\n") + + #STATISTICAL TERM EXTRACTION + + def ngram_calculation (self,nmin,nmax,minfreq=2): + '''Performs the calculation of ngrams.''' + self.ngrams=FreqDist() + self.tokens=FreqDist() + self.n_nmin=nmin + self.n_max=nmax + + with self.conn: + self.cur.execute('SELECT segment from sl_corpus') + + for self.s in self.cur.fetchall(): + self.segment=self.s[0] + for self.n in range(nmin,nmax+2): #we calculate one order bigger in order to detect nested candidates + #self.ngs=ngrams(self.sl_tokenizer.tokenize(self.segment), self.n) + self.ngs=ngrams(self.segment.split(" "), self.n) + for self.ng in self.ngs: + self.ngrams[self.ng]+=1 + #for self.token in self.sl_tokenizer.tokenize(self.segment): + for self.token in self.segment.split(" "): + self.tokens[self.token]+=1 + + self.data=[] + for self.c in self.ngrams.most_common(): + if self.c[1]>=minfreq: + self.record=[] + self.record.append(" ".join(self.c[0])) + self.record.append(len(self.c[0])) + self.record.append(self.c[1]) + self.data.append(self.record) + with self.conn: + self.cur.executemany("INSERT INTO ngrams (ngram, n, frequency) VALUES (?,?,?)",self.data) + self.conn.commit() + + self.data=[] + for self.c in self.tokens.most_common(): + self.record=[] + self.record.append(self.c[0]) + self.record.append(self.c[1]) + self.data.append(self.record) + with self.conn: + self.cur.executemany("INSERT INTO tokens (token, frequency) VALUES (?,?)",self.data) + self.conn.commit() + + def statistical_term_extraction(self,minfreq=2): + '''Performs an statistical term extraction using the extracted ngrams (ngram_calculation should be executed first) Loading stop-words is advisable. ''' + self.cur.execute("DELETE FROM term_candidates") + self.conn.commit() + self.cur.execute("SELECT ngram, n, frequency FROM ngrams order by frequency desc") + self.results=self.cur.fetchall() + self.data=[] + for self.a in self.results: + self.ng=self.a[0].split(" ") + self.include=True + if self.ng[0].lower() in self.sl_stopwords: self.include=False + if self.ng[-1].lower() in self.sl_stopwords: self.include=False + for self.i in range(1,len(self.ng)): + if self.ng[self.i].lower() in self.sl_inner_stopwords: + self.include=False + if self.include: + self.record=[] + self.record.append(self.a[0]) + self.record.append(self.a[1]) + self.record.append(self.a[2]) + self.record.append("freq") + self.record.append(self.a[2]) + self.data.append(self.record) + if self.a[2]<minfreq: + break + + with self.conn: + self.cur.executemany("INSERT INTO term_candidates (candidate, n, frequency, measure, value) VALUES (?,?,?,?,?)",self.data) + self.conn.commit() + + + def case_normalization(self,verbose=False): + ''' + Performs case normalization. If a capitalized term exists as non-capitalized, the capitalized one will be deleted and the frequency of the non-capitalized one will be increased by the frequency of the capitalized. + ''' + self.cur.execute("SELECT candidate,frequency FROM term_candidates") + self.results=self.cur.fetchall() + self.auxiliar={} + for self.r in self.results: + self.auxiliar[self.r[0]]=self.r[1] + for self.a in self.results: + if not self.a[0]==self.a[0].lower() and self.a[0].lower() in self.auxiliar: + #self.term_candidates.inc(c[0].lower(),self.term_candidates[c[0]]) + #self.term_candidates[c[0].lower()]+=self.term_candidates[c[0]] + #self.term_candidates.pop(c[0]) + self.terma=self.a[0] + self.termb=self.a[0].lower() + self.freqa=self.a[1] + self.freqb=self.auxiliar[self.termb] + + self.n=len(self.termb.split(" ")) + self.freqtotal=self.freqa+self.freqb + if verbose: + print(self.terma,self.freqa,"-->",self.termb,self.freqb,"-->",self.freqtotal) + self.cur.execute('DELETE FROM term_candidates WHERE candidate=?', (self.terma,)) + self.cur.execute('DELETE FROM term_candidates WHERE candidate=?', (self.termb,)) + #self.cur.execute("INSERT INTO term_candidates (candidate, n, frequency) VALUES (?,?,?)",(self.termb,self.n,self.freqtotal,)) + self.cur.execute("INSERT INTO term_candidates (candidate, n, frequency, measure, value) VALUES (?,?,?,?,?)",(self.termb,self.n,self.freqtotal,"freq",self.freqtotal)) + self.conn.commit() + + def nest_normalization(self,percent=10,verbose=False): + ''' + Performs a normalization of nested term candidates. If an n-gram candidate A is contained in a n+1 candidate B and freq(A)==freq(B) or they are close values (determined by the percent parameter, A is deleted B remains as it is) + ''' + self.cur.execute("SELECT candidate,frequency,n FROM term_candidates order by frequency desc") + self.results=self.cur.fetchall() + for self.a in self.results: + + self.ta=self.a[0] + self.fa=self.a[1] + self.na=self.a[2] + self.nb=self.na+1 + self.fmax=self.fa+self.fa*percent/100 + self.fmin=self.fa-self.fa*percent/100 + self.cur.execute("SELECT candidate,frequency FROM term_candidates where frequency <="+str(self.fmax)+" and frequency>="+str(self.fmin)+" and n ="+str(self.nb)+ " and n<="+str(self.n_max)) + self.results2=self.cur.fetchall() + for self.b in self.results2: + self.tb=self.b[0] + self.fb=self.b[1] + #if abs(self.fa-self.fb)<=max(self.fa,self.fb)/percent: + if not self.ta==self.tb and not self.tb.find(self.ta)==-1: + + self.cur.execute('DELETE FROM term_candidates WHERE candidate=?', (self.ta,)) + if verbose: + print(str(self.fa),self.ta,"-->",str(self.fb),self.tb) + + self.conn.commit() + + def regexp_exclusion(self,verbose=False): + '''Deletes term candidates matching a set of regular expresions loaded with the load_sl_exclusion_regexps method.''' + self.cur.execute("SELECT sl_exclusion_regexp FROM sl_exclusion_regexps") + self.results=self.cur.fetchall() + for self.r in self.results: + self.nregexp=len(self.r[0].split(" ")) + self.exreg=self.r[0] + self.cur.execute("SELECT candidate FROM term_candidates where n<="+str(self.n_max)) + self.results=self.cur.fetchall() + self.cexreg=re.compile(self.exreg) + for self.a in self.results: + self.candidate=self.a[0] + self.ncandidate=len(self.candidate.split(" ")) + self.match=re.match(self.cexreg,self.candidate) + #self.match=re.match(r'\W+$',self.candidate) + + if not self.match==None and self.nregexp==self.ncandidate: + self.cur.execute('DELETE FROM term_candidates WHERE candidate=?', (self.candidate,)) + if verbose: + print(self.exreg,"-->",self.candidate) + self.conn.commit() + + #EVALUATION + + + + def evaluate_pos(self,limit,order="desc",iterations=1000,ignore_case=True): + '''Performs the evaluation of the term candidates using the evaluation_terms loaded with the load_evaluation_terms method.''' + self.correct=0 + self.total=0 + with self.conn: + for i in range(0,iterations): + if order=="desc": + self.cur.execute("SELECT candidate from term_candidates where n<="+str(self.n_max)+" order by value desc, frequency desc, random() limit "+str(limit)) + elif order=="asc": + self.cur.execute("SELECT candidate from term_candidates where n<="+str(self.n_max)+" order by value asc, frequency desc, random() limit "+str(limit)) + else: + raise NameError('Order must be desc (decending) or asc (ascending). Defaulf value: desc') + #self.cur.execute("SELECT candidate from term_candidates order by id limit "+str(limit)) + for self.s in self.cur.fetchall(): + self.total+=1 + self.candidate=self.s[0] + if ignore_case: + if self.candidate in self.evaluation_terms: + self.correct+=1 + elif self.candidate.lower() in self.evaluation_terms: + self.correct+=1 + else: + if self.candidate in self.evaluation_terms: + self.correct+=1 + self.correct=self.correct/iterations + self.total=self.total/iterations + + try: + self.precisio=100*self.correct/self.total + self.recall=100*self.correct/len(self.evaluation_terms) + self.f1=2*self.precisio*self.recall/(self.precisio+self.recall) + return(limit,self.correct,self.total,self.precisio,self.recall,self.f1) + except: + return(limit,0,0,0,0,0) + + def association_measures(self,measure="raw_freq",n=2): + self.measurename=measure + self.bigram_measures = myBigramAssocMeasures() + self.trigram_measures = myTrigramAssocMeasures() + self.fd_tokens=nltk.FreqDist() + self.fd_bigrams=nltk.FreqDist() + self.fd_trigrams=nltk.FreqDist() + self.wildcard_fd=nltk.FreqDist() + self.cur.execute("SELECT token,frequency from tokens") + for self.s in self.cur.fetchall(): + self.aux=(self.s[0]) + self.fd_tokens[self.aux]+=self.s[1] + + self.textcorpus=[] + self.cur.execute("SELECT segment from sl_corpus") + for self.segment in self.cur.fetchall(): + #self.textcorpus.extend(self.sl_tokenizer.tokenize(self.segment[0])) + self.textcorpus.extend(self.segment[0].split(" ")) + + #BIGRAMS + if n==2: + self.cur.execute("SELECT ngram,frequency from ngrams where n=2") + for self.s in self.cur.fetchall(): + self.aux=(self.s[0].split(" ")[0],self.s[0].split(" ")[1]) + self.fd_bigrams[self.aux]+=self.s[1] + #self.bigram_finder=BigramCollocationFinder(self.fd_tokens, self.fd_bigrams) + self.bigram_finder=BigramCollocationFinder.from_words(self.textcorpus) + if measure=="chi_sq": + self.bigram_measure=self.bigram_finder.score_ngrams(self.bigram_measures.chi_sq) + elif measure=="chi_sq_2g": + self.bigram_measure=self.bigram_finder.score_ngrams(self.bigram_measures.chi_sq_2g) + elif measure=="fisher": + self.bigram_measure=self.bigram_finder.score_ngrams(self.bigram_measures.fisher) + elif measure=="phi_sq": + self.bigram_measure=self.bigram_finder.score_ngrams(self.bigram_measures.phi_sq) + elif measure=="phi_sq_2g": + self.bigram_measure=self.bigram_finder.score_ngrams(self.bigram_measures.phi_sq_2g) + elif measure=="dice": + self.bigram_measure=self.bigram_finder.score_ngrams(self.bigram_measures.dice) + elif measure=="dice_2g": + self.bigram_measure=self.bigram_finder.score_ngrams(self.bigram_measures.dice_2g) + elif measure=="my_dice": + self.bigram_measure=self.bigram_finder.score_ngrams(self.bigram_measures.my_dice) + elif measure=="jaccard": + self.bigram_measure=self.bigram_finder.score_ngrams(self.bigram_measures.jaccard) + elif measure=="jaccard_2g": + self.bigram_measure=self.bigram_finder.score_ngrams(self.bigram_measures.jaccard_2g) + elif measure=="likelihood_ratio": + self.bigram_measure=self.bigram_finder.score_ngrams(self.bigram_measures.likelihood_ratio) + elif measure=="loglikelihood_2g": + self.bigram_measure=self.bigram_finder.score_ngrams(self.bigram_measures.loglikelihood_2g) + elif measure=="pmi": + self.bigram_measure=self.bigram_finder.score_ngrams(self.bigram_measures.pmi) + elif measure=="pmi_2g": + self.bigram_measure=self.bigram_finder.score_ngrams(self.bigram_measures.pmi_2g) + elif measure=="poisson_stirling": + self.bigram_measure=self.bigram_finder.score_ngrams(self.bigram_measures.poisson_stirling) + elif measure=="poisson_stirling_2g": + self.bigram_measure=self.bigram_finder.score_ngrams(self.bigram_measures.poisson_stirling_2g) + elif measure=="student_t": + self.bigram_measure=self.bigram_finder.score_ngrams(self.bigram_measures.student_t) + elif measure=="t_score_2g": + self.bigram_measure=self.bigram_finder.score_ngrams(self.bigram_measures.t_score_2g) + elif measure=="mi_like": + self.bigram_measure=self.bigram_finder.score_ngrams(self.bigram_measures.mi_like) + elif measure=="raw_freq": + self.bigram_measure=self.bigram_finder.score_ngrams(self.bigram_measures.raw_freq) + + elif measure=="tmi_2g": + self.bigram_measure=self.bigram_finder.score_ngrams(self.bigram_measures.tmi_2g) + + elif measure=="odds_2g": + self.bigram_measure=self.bigram_finder.score_ngrams(self.bigram_measures.odds_2g) + + elif measure=="MI": + self.bigram_measure=self.bigram_finder.score_ngrams(self.bigram_measures.MI) + elif measure=="MI2": + self.bigram_measure=self.bigram_finder.score_ngrams(self.bigram_measures.MI2) + elif measure=="MI3": + self.bigram_measure=self.bigram_finder.score_ngrams(self.bigram_measures.MI3) + + elif measure=="my_dice": + self.bigram_measure=self.bigram_finder.score_ngrams(self.bigram_measures.my_dice) + elif measure=="t_score": + self.bigram_measure=self.bigram_finder.score_ngrams(self.bigram_measures.t_score) + elif measure=="log_likelihood_ratio": + self.bigram_measure=self.bigram_finder.score_ngrams(self.bigram_measures.log_likelihood_ratio) + + elif measure=="log_likelihood_ratio_TEXTNSP": + self.bigram_measure=self.bigram_finder.score_ngrams(self.bigram_measures.log_likelihood_ratio_TEXTNSP) + elif measure=="tmi": + self.bigram_measure=self.bigram_finder.score_ngrams(self.bigram_measures.tmi) + + + elif measure=="poisson_stirling_TEXTNSP": + self.bigram_measure=self.bigram_finder.score_ngrams(self.bigram_measures.poisson_stirling_TEXTNSP) + + + elif measure=="chi_squared": + self.bigram_measure=self.bigram_finder.score_ngrams(self.bigram_measures.chi_squared) + + elif measure=="jaccard_TEXTNSP": + self.bigram_measure=self.bigram_finder.score_ngrams(self.bigram_measures.jaccard_TEXTNSP) + + elif measure=="pmi_TEXTNSP": + self.bigram_measure=self.bigram_finder.score_ngrams(self.bigram_measures.pmi_TEXTNSP) + + + elif measure=="phi_sq_TEXTNSP": + self.bigram_measure=self.bigram_finder.score_ngrams(self.bigram_measures.phi_sq_TEXTNSP) + + + else: + print(sys.exc_info()[0]) + raise NameError('Association measure not implemented') + self.data=[] + for self.nose in self.bigram_measure: + self.record=[] + self.term_candidate=" ".join(self.nose[0]) + + self.mvalue=self.nose[1] + self.record.append(measure) + self.record.append(self.mvalue) + self.record.append(self.term_candidate) + self.data.append(self.record) + elif n==3: + + #TRIGRAMS + self.cur.execute("SELECT ngram,frequency from ngrams where n=2") + for self.s in self.cur.fetchall(): + self.aux=(self.s[0].split(" ")[0],self.s[0].split(" ")[1]) + self.fd_bigrams[self.aux]+=self.s[1] + + self.cur.execute("SELECT ngram,frequency from ngrams where n=3") + for self.s in self.cur.fetchall(): + self.wild=(self.s[0].split(" ")[0],self.s[0].split(" ")[2]) + self.aux=(self.s[0].split(" ")[0],self.s[0].split(" ")[1],self.s[0].split(" ")[2]) + self.fd_trigrams[self.aux]+=self.s[1] + self.wildcard_fd[self.wild]+=self.s[1] + + #self.trigram_finder=TrigramCollocationFinder(self.fd_tokens, self.fd_bigrams, self.wildcard_fd, self.fd_trigrams) + + '''Construct a TrigramCollocationFinder, given FreqDists for + appearances of words, bigrams, two words with any word between them, + and trigrams.''' + self.trigram_finder=TrigramCollocationFinder.from_words(self.textcorpus) + if self.measurename=="chi_sq": + self.trigram_measure=self.trigram_finder.score_ngrams(self.trigram_measures.chi_sq) + + elif self.measurename=="jaccard": + self.trigram_measure=self.trigram_finder.score_ngrams(self.trigram_measures.jaccard) + elif self.measurename=="likelihood_ratio": + self.trigram_measure=self.trigram_finder.score_ngrams(self.trigram_measures.likelihood_ratio) + elif self.measurename=="pmi": + self.trigram_measure=self.trigram_finder.score_ngrams(self.trigram_measures.pmi) + elif self.measurename=="poisson_stirling": + self.trigram_measure=self.trigram_finder.score_ngrams(self.trigram_measures.poisson_stirling) + elif self.measurename=="student_t": + self.trigram_measure=self.trigram_finder.score_ngrams(self.trigram_measures.student_t) + elif self.measurename=="mi_like": + self.trigram_measure=self.trigram_finder.score_ngrams(self.trigram_measures.mi_like) + elif self.measurename=="raw_freq": + self.trigram_measure=self.trigram_finder.score_ngrams(self.trigram_measures.raw_freq) + + elif measure=="pmi_3g": + self.trigram_measure=self.trigram_finder.score_ngrams(self.trigram_measures.pmi_3g) + + elif measure=="poisson_stirling_3g": + self.trigram_measure=self.trigram_finder.score_ngrams(self.trigram_measures.poisson_stirling_3g) + + elif measure=="tmi_3g": + self.trigram_measure=self.trigram_finder.score_ngrams(self.trigram_measures.tmi_3g) + + elif measure=="loglikelihood_3g": + self.trigram_measure=self.trigram_finder.score_ngrams(self.trigram_measures.loglikelihood_3g) + else: + raise NameError('Association measure not implemented') + self.data=[] + for self.nose in self.trigram_measure: + self.record=[] + self.term_candidate=" ".join(self.nose[0]) + self.mvalue=self.nose[1] + self.record.append(self.measurename) + self.record.append(self.mvalue) + self.record.append(self.term_candidate) + self.data.append(self.record) + + + + + self.conn.executemany("UPDATE term_candidates SET measure=?,value=? where candidate=?",self.data) + self.conn.commit() + + + + def index_phrase_table(self,phrasetable): + '''Indexes a phrase table from Moses.''' + self.entrada=gzip.open(phrasetable, mode='rt') + + self.pt={} + self.continserts=0 + self.record=[] + self.data=[] + while 1: + self.linia=self.entrada.readline() + if not self.linia: + break + self.linia=self.linia.rstrip() + self.camps=self.linia.split(" ||| ") + self.source=self.camps[0].strip() + self.trad=self.camps[1].strip() + self.probs=self.camps[2].split(" ") + if not self.trad[0] in self.punctuation and not self.source[0] in self.punctuation and not self.trad[-1] in self.punctuation and not self.source[-1] in self.punctuation: + #Currently, four different phrase translation scores are computed: + #0 inverse phrase translation probability φ(f|e) + #1 inverse lexical weighting lex(f|e) + #2 direct phrase translation probability φ(e|f) + #3 direct lexical weighting lex(e|f) + #self.probtrad=float(self.probs[1]) + self.probtrad=(float(self.probs[2])*float(self.probs[3])) + #print(self.source,self.trad,self.probtrad) + self.record=[] + self.record.append(self.source) + self.record.append(self.trad) + self.record.append(self.probtrad) + self.data.append(self.record) + self.continserts+=1 + if self.continserts==self.maxinserts: + self.cur.executemany("INSERT INTO index_pt (source, target, probability) VALUES (?,?,?)",self.data) + self.data=[] + self.continserts=0 + self.conn.commit() + with self.conn: + self.cur.executemany("INSERT INTO index_pt (source, target, probability) VALUES (?,?,?)",self.data) + self.conn.commit() + + + def find_translation_ptable(self,sourceterm,maxdec=1,maxinc=1,ncandidates=5,separator=":"): + '''Finds translation equivalents in an indexed phrase table table. Requires an indexed phrase table and a a list of terms separated by ":". + The number of translation candidates can be fixed, as well as the maximum decrement and increment of the number of tokens of the translation candidate''' + #select target from index_pt where source="international conflict"; + self.cur.execute('SELECT target,probability FROM index_pt where source =?',(sourceterm,)) + self.results=self.cur.fetchall() + self.targetcandidates={} + for self.a in self.results: + self.targetterm=self.a[0] + self.probability=float(self.a[1]) + self.tttokens=self.targetterm.split(" ") + + if not self.tttokens[0] in self.tl_stopwords and not self.tttokens[-1] in self.tl_stopwords and len(self.tttokens)>=len(sourceterm.split(" "))-maxdec and len(self.tttokens)<=len(sourceterm.split(" "))+maxinc: + self.targetcandidates[self.targetterm]=self.probability + self.sorted_x = sorted(self.targetcandidates.items(), key=operator.itemgetter(1),reverse=True) + self.results=[] + for self.s in self.sorted_x: + self.results.append(self.s[0].replace(":",";")) + return(separator.join(self.results[0:ncandidates])) + + + + def start_freeling_api(self,LANG): + + freelingpath='/home/aoliverg/eines/Freeling-4.0/FreeLing-4.0/APIs/python' + + try: + sys.path.append(freelingpath) + import freeling + except: + #pass + print("No Freeling API available. Verify Freeling PATH: "+freelingpath) + + freeling.util_init_locale("default"); + + # create language analyzer + self.la1=freeling.lang_ident(self.DATA+"common/lang_ident/ident.dat"); + + # create options set for maco analyzer. Default values are Ok, except for data files. + self.op1= freeling.maco_options(LANG); + self.op1.set_data_files( "", + self.DATA + "common/punct.dat", + self.DATA + LANG + "/dicc.src", + self.DATA + LANG + "/afixos.dat", + "", + self.DATA + LANG + "/locucions.dat", + self.DATA + LANG + "/np.dat", + self.DATA + LANG + "/quantities.dat", + self.DATA + LANG + "/probabilitats.dat"); + + # create analyzers + self.tk1=freeling.tokenizer(self.DATA+LANG+"/tokenizer.dat"); + self.sp1=freeling.splitter(self.DATA+LANG+"/splitter.dat"); + self.sid1=self.sp1.open_session(); + self.mf1=freeling.maco(self.op1); + + # activate mmorpho odules to be used in next call + self.mf1.set_active_options(False, True, True, False, # select which among created + True, True, False, True, # submodules are to be used. + True, False, True, True ); # default: all created submodules are used + + # create tagger, sense anotator, and parsers + self.tg1=freeling.hmm_tagger(self.DATA+LANG+"/tagger.dat",True,2); + + def tag_freeling_api(self,corpus="source"): + with self.conn: + self.data=[] + if corpus=="source": + self.cur.execute('SELECT id,segment from sl_corpus') + elif corpus=="target": + self.cur.execute('SELECT id,segment from tl_corpus') + for self.s in self.cur.fetchall(): + self.id=self.s[0] + self.segment=self.s[1] + self.l1 = self.tk1.tokenize(self.segment); + self.ls1 = self.sp1.split(self.sid1,self.l1,True); + self.ls1 = self.mf1.analyze(self.ls1); + self.ls1 = self.tg1.analyze(self.ls1); + self.ttsentence=[] + for self.s in self.ls1 : + self.ws = self.s.get_words(); + for self.w in self.ws : + self.form=self.w.get_form() + self.lemma=self.w.get_lemma() + self.tag=self.w.get_tag() + self.ttsentence.append(self.form+"|"+self.lemma+"|"+self.tag) + self.ttsentence=" ".join(self.ttsentence) + self.record=[] + self.record.append(self.id) + self.record.append(self.ttsentence) + self.data.append(self.record) + if self.continserts==self.maxinserts: + if corpus=="source": + self.cur.executemany("INSERT INTO sl_tagged_corpus (id, tagged_segment) VALUES (?,?)",self.data) + if corpus=="target": + self.cur.executemany("INSERT INTO tl_tagged_corpus (id, tagged_segment) VALUES (?,?)",self.data) + self.data=[] + self.continserts=0 + with self.conn: + if corpus=="source": + self.cur.executemany("INSERT INTO sl_tagged_corpus (id, tagged_segment) VALUES (?,?)",self.data) + if corpus=="target": + self.cur.executemany("INSERT INTO tl_tagged_corpus (id, tagged_segment) VALUES (?,?)",self.data) + def save_sl_tagged_corpus(self,outputfile,encoding="utf-8"): + self.sortida=codecs.open(outputfile,"w",encoding=encoding) + self.cur.execute('SELECT tagged_segment from sl_tagged_corpus') + for self.s in self.cur.fetchall(): + self.tagged_segment=self.s[0] + self.sortida.write(self.tagged_segment+"\n") + + + def tagged_ngram_calculation (self,nmin=2,nmax=3,minfreq=2): + '''Calculates the tagged ngrams.''' + self.ngrams=FreqDist() + self.n_nmin=nmin + self.n_max=nmax + with self.conn: + self.data=[] + self.record=[] + self.record.append(self.n_min) + self.data.append(self.record) + #self.conn.executemany("UPDATE configuration SET n_min=? where id=0",self.data) + self.data=[] + self.record=[] + self.record.append(self.n_max) + self.data.append(self.record) + #self.conn.executemany("UPDATE configuration SET n_max=? where id=0",self.data) + #cur.execute("UPDATE Contacts SET FirstName = ? WHERE LastName = ?", (Fname, Lname)) + + self.conn.commit() + + with self.conn: + self.cur.execute('SELECT tagged_segment from sl_tagged_corpus') + + for self.s in self.cur.fetchall(): + self.segment=self.s[0] + + for self.n in range(nmin,nmax+2): #we calculate one order bigger in order to detect nested candidates + self.ngs=ngrams(self.segment.split(" "), self.n) + for self.ng in self.ngs: + self.ngrams[self.ng]+=1 + + self.data=[] + for self.c in self.ngrams.most_common(): + if self.c[1]>=minfreq: + self.candidate=[] + for self.ngt in self.c[0]: + self.candidate.append(self.ngt.split("|")[0]) + self.candidate=" ".join(self.candidate) + self.record=[] + self.record.append(self.candidate) + self.record.append(" ".join(self.c[0])) + self.record.append(len(self.c[0])) + self.record.append(self.c[1]) + self.data.append(self.record) + with self.conn: + self.cur.executemany("INSERT INTO tagged_ngrams (ngram, tagged_ngram, n, frequency) VALUES (?,?,?,?)",self.data) + self.conn.commit() + + def translate_linguistic_pattern(self,pattern): + + self.aux=[] + for self.ptoken in pattern.split(" "): + self.auxtoken=[] + self.ptoken=self.ptoken.replace(".*","[^\s]+") #ATENCIÓ AIXÓ ÉS NOU, VERIFICAR SI CAL + for self.pelement in self.ptoken.split("|"): + if self.pelement=="#": + self.auxtoken.append("([^\s]+?)") + elif self.pelement=="": + self.auxtoken.append("[^\s]+?") + else: + if self.pelement.startswith("#"): + self.auxtoken.append("("+self.pelement.replace("#","")+")") + else: + self.auxtoken.append(self.pelement) + self.aux.append("\|".join(self.auxtoken)) + self.tp="("+" ".join(self.aux)+")" + #self.tpatterns.append(self.tp) + return(self.tp) + + def load_linguistic_patterns(self,file, encoding="utf-8"): + '''Loads the linguistic patterns to use with linguistic terminology extraction.''' + self.entrada=codecs.open(file,"r",encoding=encoding) + self.linguistic_patterns=[] + self.data=[] + self.record=[] + for self.linia in self.entrada: + self.linia=self.linia.rstrip() + self.pattern=self.translate_linguistic_pattern(self.linia) + self.record.append(self.pattern) + self.data.append(self.record) + self.record=[] + with self.conn: + self.cur.executemany("INSERT INTO linguistic_patterns (linguistic_pattern) VALUES (?)",self.data) + + + + def linguistic_term_extraction(self,minfreq=2): + '''Performs an linguistic term extraction using the extracted tagged ngrams (tagged_ngram_calculation should be executed first). ''' + self.linguistics_patterns=[] + with self.conn: + self.cur.execute("SELECT linguistic_pattern from linguistic_patterns") + for self.lp in self.cur.fetchall(): + self.linguistic_pattern=self.lp[0] + self.linguistic_patterns.append("^"+self.linguistic_pattern+"$") + + self.cur.execute("SELECT tagged_ngram, n, frequency FROM tagged_ngrams order by frequency desc") + self.results=self.cur.fetchall() + self.data=[] + + for self.a in self.results: + self.include=True + self.ng=self.a[0] + self.n=self.a[1] + self.frequency=self.a[2] + if self.ng.split(" ")[0].split("|")[1].lower() in self.sl_stopwords: self.include=False + if self.ng.split(" ")[-1].split("|")[1].lower() in self.sl_stopwords: self.include=False + if self.frequency<minfreq: + break + if self.include: + for self.pattern in self.linguistic_patterns: + self.match=re.search(self.pattern,self.ng) + + if self.match: + if self.match.group(0)==self.ng: + + self.candidate=" ".join(self.match.groups()[1:]) + self.record=[] + self.record.append(self.candidate) + self.record.append(self.n) + self.record.append(self.frequency) + self.record.append("freq") + self.record.append(self.frequency) + self.data.append(self.record) + + with self.conn: + #self.cur.executemany("INSERT INTO term_candidates (candidate, n, frequency) VALUES (?,?,?)",self.data) + self.cur.executemany("INSERT INTO term_candidates (candidate, n, frequency, measure, value) VALUES (?,?,?,?,?)",self.data) + self.conn.commit() + + #eliminem candidats repetits + self.cur.execute("SELECT candidate, n, frequency FROM term_candidates") + self.results=self.cur.fetchall() + self.tcaux={} + for self.a in self.results: + if not self.a[0] in self.tcaux: + self.tcaux[self.a[0]]=self.a[2] + else: + self.tcaux[self.a[0]]+=self.a[2] + + self.cur.execute("DELETE FROM term_candidates") + self.conn.commit() + self.data=[] + for self.tc in self.tcaux: + self.record=[] + self.record.append(self.tc) + self.record.append(len(self.tc.split(" "))) + self.record.append(self.tcaux[self.tc]) + self.record.append("freq") + self.record.append(self.tcaux[self.tc]) + self.data.append(self.record) + with self.conn: + #self.cur.executemany("INSERT INTO term_candidates (candidate, n, frequency) VALUES (?,?,?)",self.data) + self.cur.executemany("INSERT INTO term_candidates (candidate, n, frequency, measure, value) VALUES (?,?,?,?,?)",self.data) + self.conn.commit() + + + def learn_linguistic_patterns(self,outputfile,showfrequencies=False,encoding="utf-8",verbose=True,representativity=100): + self.learntpatterns={} + self.sortida=codecs.open(outputfile,"w",encoding=encoding) + self.acufreq=0 + with self.conn: + self.cur.execute("SELECT sl_term FROM evaluation_terms") + for self.s in self.cur.fetchall(): + self.cur.execute("SELECT tagged_ngram, n, frequency FROM tagged_ngrams WHERE ngram= ?", (self.s[0],)) + self.results=self.cur.fetchall() + + if len(self.results)>0: + for self.a in self.results: + self.ng=self.a[0] + self.n=self.a[1] + self.frequency=self.a[2] + self.candidate=[] + self.ngtokenstag=self.ng.split(" ") + for self.ngt in self.ngtokenstag: + self.candidate.append(self.ngt.split("|")[0]) + self.candidate=" ".join(self.candidate) + self.t2=self.ng.split(" ") + self.t1=self.candidate.split(" ") + self.patternbrut=[] + for self.position in range(0,self.n): + self.t2f=self.t2[self.position].split("|")[0] + self.t2l=self.t2[self.position].split("|")[1] + self.t2t=self.t2[self.position].split("|")[2] + self.patternpart="" + if self.t1[self.position]==self.t2l: + self.patternpart="|#|"+self.t2t + elif self.t1[self.position]==self.t2f: + self.patternpart="#||"+self.t2t + self.patternbrut.append(self.patternpart) + self.pattern=" ".join(self.patternbrut) + if self.pattern in self.learntpatterns: + self.learntpatterns[self.pattern]+=self.n + self.acufreq+=self.n + else: + self.learntpatterns[self.pattern]=self.n + self.acufreq+=self.n + self.sorted_x = sorted(self.learntpatterns.items(), key=operator.itemgetter(1),reverse=True) + self.results=[] + self.acufreq2=0 + for self.s in self.sorted_x: + self.percent=100*self.acufreq2/self.acufreq + if self.percent>representativity: + break + self.acufreq2+=self.s[1] + if showfrequencies: + cadena=str(self.s[1])+"\t"+self.s[0] + else: + cadena=self.s[0] + self.sortida.write(cadena+"\n") + if verbose: + print(cadena) + + def find_translation_pcorpus(self,slterm,maxdec=1,maxinc=1,ncandidates=5,separator=":"): + self.nmin=len(slterm.split(" "))-maxdec + self.nmax=len(slterm.split(" "))+maxinc + self.tlngrams=FreqDist() + with self.conn: + self.cur.execute('SELECT id, segment from sl_corpus') + + for self.s in self.cur.fetchall(): + self.segment=self.s[1] + self.id=self.s[0] + + if self.segment.find(slterm)>-1: + self.cur2.execute('SELECT segment from tl_corpus where id="'+str(self.id)+'"') + for self.s2 in self.cur2.fetchall(): + self.tl_segment=self.s2[0] + for self.n in range(self.nmin,self.nmax+1): + #self.tlngs=ngrams(self.tl_tokenizer.tokenize(self.tl_segment), self.n) + self.tlngs=ngrams(self.tl_segment.split(" "), self.n) + for self.tlng in self.tlngs: + if not self.tlng[0] in self.tl_stopwords and not self.tlng[-1] in self.tl_stopwords: + self.tlngrams[self.tlng]+=1 + self.resultlist=[] + for self.c in self.tlngrams.most_common(ncandidates): + self.resultlist.append(" ".join(self.c[0])) + + return(separator.join(self.resultlist)) + + +#TSR + + def tsr(self,termsfile,encoding="utf-8", type="strict",max_iterations=10000000000): #IMPLEMENTED ONLY FOR BIGRAMS + self.component={} + self.firstcomponent={} + self.middlecomponent={} + self.lastcomponent={} + self.entrada=codecs.open(termsfile,"r",encoding=encoding) + for self.linia in self.entrada: + self.linia=self.linia.rstrip() + self.camps=self.linia.split(" ") + if len(self.camps)==1: #UNIGRAMS + self.firstcomponent[self.camps[0]]=1 + self.lastcomponent[self.camps[0]]=1 + if len(self.camps)>=2: + self.firstcomponent[self.camps[0]]=1 + self.lastcomponent[self.camps[-1]]=1 + self.component[self.camps[0]]=1 + self.component[self.camps[-1]]=1 + if len(self.camps)>=3: + for self.i in range(1,len(self.camps)): + self.middlecomponent[self.camps[self.i]]=1 + self.component[self.camps[self.i]]=1 + self.new=True + self.newcandidates={} #candidate-frequency + self.hashmeasure={} + self.hashvalue={} + + self.newcandidatestempstric={} #candidate-frequency + self.hashmeasuretempstrict={} + self.hashvaluetempstric={} + + self.newcandidatestempflexible={} #candidate-frequency + self.hashmeasuretempflexible={} + self.hashvaluetempflexible={} + + self.newcandidatestempcombined={} #candidate-frequency + self.hashmeasuretempcombined={} + self.hashvaluetempcombined={} + + self.iterations=0 + while self.new: + self.iterations+=1 + print("ITERATION",self.iterations) + self.new=False + self.cur.execute("SELECT candidate,n,frequency,measure,value FROM term_candidates") + self.results=self.cur.fetchall() + self.auxiliar={} + for self.r in self.results: + self.candidate=self.r[0] + self.n=self.r[1] + self.frequency=self.r[2] + self.measure="tsr"#self.r[3] + self.value=max_iterations-self.iterations#self.r[4] + self.rcamps=self.candidate.split(" ") + if type=="strict": + if self.rcamps[0] in self.firstcomponent and self.rcamps[-1] in self.lastcomponent: + if not self.candidate in self.newcandidates: + #print(self.r) + self.newcandidates[self.candidate]=self.frequency + self.hashmeasure[self.candidate]=self.measure + self.hashvalue[self.candidate]=self.value + self.new=True + self.firstcomponent[self.rcamps[0]]=1 + self.lastcomponent[self.rcamps[-1]]=1 + elif type=="flexible": + if self.rcamps[0] in self.firstcomponent or self.rcamps[-1] in self.lastcomponent: + if not self.candidate in self.newcandidates: + self.newcandidates[self.candidate]=self.frequency + self.hashmeasure[self.candidate]=self.measure + self.hashvalue[self.candidate]=self.value + self.new=True + self.firstcomponent[self.rcamps[0]]=1 + self.lastcomponent[self.rcamps[-1]]=1 + self.component[self.rcamps[0]]=1 + self.component[self.rcamps[-1]]=1 + elif type=="combined": + if self.iterations==1: + if self.rcamps[0] in self.firstcomponent and self.rcamps[-1] in self.lastcomponent: + if not self.candidate in self.newcandidates: + self.newcandidates[self.candidate]=self.frequency + self.hashmeasure[self.candidate]=self.measure + self.hashvalue[self.candidate]=self.value + self.new=True + self.firstcomponent[self.rcamps[0]]=1 + self.lastcomponent[self.rcamps[-1]]=1 + self.component[self.rcamps[0]]=1 + self.component[self.rcamps[-1]]=1 + else: + if self.rcamps[0] in self.firstcomponent or self.rcamps[-1] in self.lastcomponent: + if not self.candidate in self.newcandidates: + self.newcandidatestempcombined[self.candidate]=self.frequency + self.hashmeasuretempcombined[self.candidate]=self.measure + self.hashvaluetempcombined[self.candidate]=self.value + self.new=True + self.firstcomponent[self.rcamps[0]]=1 + self.lastcomponent[self.rcamps[-1]]=1 + self.component[self.rcamps[0]]=1 + self.component[self.rcamps[-1]]=1 + + + if self.iterations>=max_iterations: + break + print(self.iterations,self.new) + with self.conn: + self.cur.execute('DELETE FROM term_candidates') + self.conn.commit() + + + data=[] + for self.c in self.newcandidates: + self.termb=self.c + self.n=len(self.c.split(" ")) + self.freqtotal=self.newcandidates[self.c] + self.measure=self.hashmeasure[self.c] + self.value=self.hashvalue[self.c] + record=[] + record.append(self.termb) + record.append(self.n) + record.append(self.freqtotal) + record.append(self.measure) + record.append(self.value) + data.append(record) + with self.conn: + self.cur.executemany("INSERT INTO term_candidates (candidate, n, frequency, measure, value) VALUES (?,?,?,?,?)",data) + + self.conn.commit() + +def L_LLR(a,b,c): + '''Auxiliar function to calculate Log Likelihood Ratio''' + L=(c**a)*((1-c)**(b-a)) + return(L) + +class myBigramAssocMeasures(nltk.collocations.BigramAssocMeasures): + """ + A collection of bigram association measures. Each association measure + is provided as a function with three arguments:: + + bigram_score_fn(n_ii, (n_ix, n_xi), n_xx) + + The arguments constitute the marginals of a contingency table, counting + the occurrences of particular events in a corpus. The letter i in the + suffix refers to the appearance of the word in question, while x indicates + the appearance of any word. Thus, for example: + + n_ii counts (w1, w2), i.e. the bigram being scored + n_ix counts (w1, *) + n_xi counts (*, w2) + n_xx counts (*, *), i.e. any bigram + + This may be shown with respect to a contingency table:: + + w1 ~w1 + ------ ------ + w2 | n_ii | n_oi | = n_xi + ------ ------ + ~w2 | n_io | n_oo | + ------ ------ + = n_ix TOTAL = n_xx + + Amb la terminologia de Pazienza + + w1 ~w1 + ------ ------ + w2 | n_ii O11| n_oi O12| = n_xi + ------ ------ + ~w2 | n_io O21| n_oo O22| + ------ ------ + = n_ix TOTAL = n_xx + + N=O11+O12+O21+O22= n_xx + R1=O11+O12 = n_xi + R2=O21+O22 + C1=O11+O21=n_ix + C2=O12+O22= n_oi+n_oo + + TENIM: n_ii, n_ix_xi_tuple, n_xx + n_io=n_ix-n_ii + n_oi=n_xi-n_ii + n_oo=n_xx-n_ix-n_xi + """ + #NOVES + + def chi_sq_2g(self,n_ii, n_ix_xi_tuple, n_xx): + '''chi_sq - Pearson's chi-squared according to NSP''' + (n_ix, n_xi) = n_ix_xi_tuple + n_oo=n_xx-n_ix-n_xi + n_io=n_ix-n_ii + n_oi=n_xi-n_ii + n_oo=n_xx-n_ix-n_xi + + n11=n_ii + n12=n_io + n21=n_oi + n22=n_oo + n1p=n11+n12 + np1=n11+n21 + n2p=n21+n22 + np2=n12+n22 + npp=n_xx + + m11 = (n1p*np1/npp) + m12 = (n1p*np2/npp) + m21 = (np1*n2p/npp) + m22 = (n2p*np2/npp) + + x2 = 2 * (((n11 - m11)/m11)**2 + ((n12 - m12)/m12)**2 + ((n21 - m21)/m21)**2 + ((n22 -m22)/m22)**2) + return(x2) + def phi_sq_2g(self,n_ii, n_ix_xi_tuple, n_xx): + '''chi_sq - Pearson's chi-squared according to NSP''' + (n_ix, n_xi) = n_ix_xi_tuple + n_oo=n_xx-n_ix-n_xi + n_io=n_ix-n_ii + n_oi=n_xi-n_ii + n_oo=n_xx-n_ix-n_xi + + n11=n_ii + n12=n_io + n21=n_oi + n22=n_oo + n1p=n11+n12 + np1=n11+n21 + n2p=n21+n22 + np2=n12+n22 + npp=n_xx + + m11 = (n1p*np1/npp) + m12 = (n1p*np2/npp) + m21 = (np1*n2p/npp) + m22 = (n2p*np2/npp) + + PHI2 = ((n11 * n22) - (n21 * n21))**2/(n1p * np1 * np2 * n2p) + return(PHI2) + + def t_score_2g(self,n_ii, n_ix_xi_tuple, n_xx): + '''chi_sq - Pearson's chi-squared according to NSP''' + (n_ix, n_xi) = n_ix_xi_tuple + n_oo=n_xx-n_ix-n_xi + n_io=n_ix-n_ii + n_oi=n_xi-n_ii + n_oo=n_xx-n_ix-n_xi + + n11=n_ii + n12=n_io + n21=n_oi + n22=n_oo + n1p=n11+n12 + np1=n11+n21 + n2p=n21+n22 + np2=n12+n22 + npp=n_xx + + m11 = (n1p*np1/npp) + m12 = (n1p*np2/npp) + m21 = (np1*n2p/npp) + m22 = (n2p*np2/npp) + + m11 = n1p * np1 / npp + + T_score = (n11 - m11)/math.sqrt(n11) + + return(T_score) + def dice_2g(self,n_ii, n_ix_xi_tuple, n_xx): + '''chi_sq - Pearson's chi-squared according to NSP''' + (n_ix, n_xi) = n_ix_xi_tuple + n_oo=n_xx-n_ix-n_xi + n_io=n_ix-n_ii + n_oi=n_xi-n_ii + n_oo=n_xx-n_ix-n_xi + + n11=n_ii + n12=n_io + n21=n_oi + n22=n_oo + n1p=n11+n12 + np1=n11+n21 + n2p=n21+n22 + np2=n12+n22 + npp=n_xx + + m11 = (n1p*np1/npp) + m12 = (n1p*np2/npp) + m21 = (np1*n2p/npp) + m22 = (n2p*np2/npp) + + dice=2*n11/(np1 + n1p) + return(dice) + + def jaccard_2g(self,n_ii, n_ix_xi_tuple, n_xx): + '''chi_sq - Pearson's chi-squared according to NSP''' + (n_ix, n_xi) = n_ix_xi_tuple + n_oo=n_xx-n_ix-n_xi + n_io=n_ix-n_ii + n_oi=n_xi-n_ii + n_oo=n_xx-n_ix-n_xi + + n11=n_ii + n12=n_io + n21=n_oi + n22=n_oo + n1p=n11+n12 + np1=n11+n21 + n2p=n21+n22 + np2=n12+n22 + npp=n_xx + + m11 = (n1p*np1/npp) + m12 = (n1p*np2/npp) + m21 = (np1*n2p/npp) + m22 = (n2p*np2/npp) + + jaccard = n11 / (n11 + n12 + n21) + return(jaccard) + + def loglikelihood_2g(self,n_ii, n_ix_xi_tuple, n_xx): + '''chi_sq - Pearson's chi-squared according to NSP''' + (n_ix, n_xi) = n_ix_xi_tuple + n_oo=n_xx-n_ix-n_xi + n_io=n_ix-n_ii + n_oi=n_xi-n_ii + n_oo=n_xx-n_ix-n_xi + + n11=n_ii + n12=n_io + n21=n_oi + n22=n_oo + n1p=n11+n12 + np1=n11+n21 + n2p=n21+n22 + np2=n12+n22 + npp=n_xx + + m11 = (n1p*np1/npp) + m12 = (n1p*np2/npp) + m21 = (np1*n2p/npp) + m22 = (n2p*np2/npp) + try: + LogLikelihood = 2 * (n11 * math.log((n11/m11),2) + n12 * math.log((n12/m12),2) + n21 * math.log((n21/m21),2) + n22 * math.log((n22/m22),2)) + except: + LogLikelihood=0 + return(LogLikelihood) + + def MI(self,n_ii, n_ix_xi_tuple, n_xx): + '''Church Mutual Information accoding to Pazienza''' + (n_ix, n_xi) = n_ix_xi_tuple + self.E11=n_xi*n_ix/n_xx + self.part=n_ii/self.E11 + self.MI=math.log(self.part,2) + return(self.MI) + + def MI2(self,n_ii, n_ix_xi_tuple, n_xx): + '''Church Mutual Information Variant accoding to Pazienza''' + (n_ix, n_xi) = n_ix_xi_tuple + self.E11=n_xi*n_ix/n_xx + self.part=(n_ii/self.E11)**2 + self.MI2=math.log(self.part,2) + return(self.MI2) + + def MI3(self,n_ii, n_ix_xi_tuple, n_xx): + '''Church Mutual Information Variant accoding to Pazienza''' + (n_ix, n_xi) = n_ix_xi_tuple + self.E11=n_xi*n_ix/n_xx + self.part=(n_ii/self.E11)**3 + self.MI3=math.log(self.part,2) + return(self.MI3) + + def pmi_2g(self,n_ii, n_ix_xi_tuple, n_xx): + '''chi_sq - Pearson's chi-squared according to NSP''' + (n_ix, n_xi) = n_ix_xi_tuple + n_oo=n_xx-n_ix-n_xi + n_io=n_ix-n_ii + n_oi=n_xi-n_ii + n_oo=n_xx-n_ix-n_xi + + n11=n_ii + n12=n_io + n21=n_oi + n22=n_oo + n1p=n11+n12 + np1=n11+n21 + n2p=n21+n22 + np2=n12+n22 + npp=n_xx + + m11 = (n1p*np1/npp) + m12 = (n1p*np2/npp) + m21 = (np1*n2p/npp) + m22 = (n2p*np2/npp) + + PMI = math.log((n11/m11),2) + return(PMI) + + def poisson_stirling_2g(self,n_ii, n_ix_xi_tuple, n_xx): + '''chi_sq - Pearson's chi-squared according to NSP''' + (n_ix, n_xi) = n_ix_xi_tuple + n_oo=n_xx-n_ix-n_xi + n_io=n_ix-n_ii + n_oi=n_xi-n_ii + n_oo=n_xx-n_ix-n_xi + + n11=n_ii + n12=n_io + n21=n_oi + n22=n_oo + n1p=n11+n12 + np1=n11+n21 + n2p=n21+n22 + np2=n12+n22 + npp=n_xx + + m11 = (n1p*np1/npp) + m12 = (n1p*np2/npp) + m21 = (np1*n2p/npp) + m22 = (n2p*np2/npp) + + PoissonStirling = n11 * ( math.log(n11,2) - math.log(m11,2) - 1) + return(PoissonStirling) + + + def tmi_2g(self,n_ii, n_ix_xi_tuple, n_xx): + '''chi_sq - Pearson's chi-squared according to NSP''' + (n_ix, n_xi) = n_ix_xi_tuple + n_oo=n_xx-n_ix-n_xi + n_io=n_ix-n_ii + n_oi=n_xi-n_ii + n_oo=n_xx-n_ix-n_xi + + n11=n_ii + n12=n_io + n21=n_oi + n22=n_oo + n1p=n11+n12 + np1=n11+n21 + n2p=n21+n22 + np2=n12+n22 + npp=n_xx + + m11 = (n1p*np1/npp) + m12 = (n1p*np2/npp) + m21 = (np1*n2p/npp) + m22 = (n2p*np2/npp) + try: + tmi = ((n11/npp) * math.log((n11/m11),) + (n12/npp) * math.log((n12/m12),2) + (n21/npp) * math.log((n21/m21),2) + (n22/npp) * math.log((n22/m22),2)) + except: + tmi=0 + return(tmi) + + def odds_2g(self,n_ii, n_ix_xi_tuple, n_xx): + '''chi_sq - Pearson's chi-squared according to NSP''' + (n_ix, n_xi) = n_ix_xi_tuple + n_oo=n_xx-n_ix-n_xi + n_io=n_ix-n_ii + n_oi=n_xi-n_ii + n_oo=n_xx-n_ix-n_xi + + n11=n_ii + n12=n_io + n21=n_oi + n22=n_oo + n1p=n11+n12 + np1=n11+n21 + n2p=n21+n22 + np2=n12+n22 + npp=n_xx + + m11 = (n1p*np1/npp) + m12 = (n1p*np2/npp) + m21 = (np1*n2p/npp) + m22 = (n2p*np2/npp) + + if n21==0:n21=1 + if n12==0:n12=1 + ODDS_RATIO = (n11*n22)/(n21*n12) + return(ODDS_RATIO) + + #VELLES + + + def my_dice(self,n_ii, n_ix_xi_tuple, n_xx): + '''Recalculation of dice accoding to Pazienza''' + (n_ix, n_xi) = n_ix_xi_tuple + n_oo=n_xx-n_ix-n_xi + + n_io=n_ix-n_ii + n_oi=n_xi-n_ii + n_oo=n_xx-n_ix-n_xi + + self.DF=2*n_ii/(n_xi+n_ix) + return(self.DF) + + def t_score(self,n_ii, n_ix_xi_tuple, n_xx): + '''Recalculation of student_t accoding to Pazienza''' + (n_ix, n_xi) = n_ix_xi_tuple + self.E11=n_xi*n_ix/n_xx + self.TS=(n_ii-self.E11)/math.sqrt(n_ii) + return(self.TS) + + def L_LLR(self,a,b,c): + '''Auxiliar function to calculate Log Likelihood Ratio''' + L=(c**a)*((1-c)**(b-a)) + return(L) + + def log_likelihood_ratio(self,n_ii, n_ix_xi_tuple, n_xx): + '''Calculation of Log Likelihood Ratio accoding to Pazienza''' + (n_ix, n_xi) = n_ix_xi_tuple + n_oo=n_xx-n_ix-n_xi + + n_io=n_ix-n_ii + n_oi=n_xi-n_ii + n_oo=n_xx-n_ix-n_xi + + r=n_xi/n_xx + r1=n_ii/n_ix + r2=n_oi/(n_oi+n_oo) + + NOM=L_LLR(n_ii,n_ix,r)*L_LLR(n_oi,(n_oi+n_oo),r) + DEN=L_LLR(n_ii,n_ix,r1)*L_LLR(n_oi,(n_oi+n_oo),r2) + if not DEN==0 and NOM/DEN>0: + self.LLR=-2*math.log((NOM/DEN),2) + else: + self.LLR=0 + return(self.LLR) + + def log_likelihood_ratio_TEXTNSP(self,n_ii, n_ix_xi_tuple, n_xx): + '''Calculation of Log Likelihood Ratio accoding to Pazienza''' + (n_ix, n_xi) = n_ix_xi_tuple + n_oo=n_xx-n_ix-n_xi + + n_io=n_ix-n_ii + n_oi=n_xi-n_ii + n_oo=n_xx-n_ix-n_xi + + m11=(n_ix*n_xi)/n_xx + m12=(n_io+n_oo)*n_xi/n_xx + m21=n_ix*(n_io+n_oo)/n_xx + m22=(n_oi+n_oo)*(n_io+n_oo)/n_xx + try: + self.LLR=2*((n_ii*math.log((n_ii/m11),2))+(n_oi*math.log((n_oi/m12),2))+(n_io*math.log((n_io/m21),2))+(n_oo*math.log((n_oo/m22),2))) + except: + self.LRR=0 + + return(self.LLR) + + def tmi(self,n_ii, n_ix_xi_tuple, n_xx): + '''Calculation of True Mutual Information according to Text:NSP''' + (n_ix, n_xi) = n_ix_xi_tuple + n_oo=n_xx-n_ix-n_xi + + n_io=n_ix-n_ii + n_oi=n_xi-n_ii + n_oo=n_xx-n_ix-n_xi + + self.E11=n_xi*n_ix/n_xx + self.PMI=math.log((n_ii/self.E11),2) + + + self.tmi=(n_ii/n_xx)*self.PMI+(n_oi/n_xx)*self.PMI+(n_io/n_xx)*self.PMI+(n_oo/n_xx)*self.PMI + print(self.E11,self.PMI,self.tmi) + return(self.tmi) + + def poisson_stirling_TEXTNSP(self,n_ii, n_ix_xi_tuple, n_xx): + '''Calculation of Log Likelihood Ratio accoding to Pazienza''' + (n_ix, n_xi) = n_ix_xi_tuple + n_oo=n_xx-n_ix-n_xi + + n_io=n_ix-n_ii + n_oi=n_xi-n_ii + n_oo=n_xx-n_ix-n_xi + + m11=(n_ix*n_xi)/n_xx + + self.PS=n_ii*(math.log((n_ii/m11),2)-1) + + return(self.PS) + + def chi_squared(self,n_ii, n_ix_xi_tuple, n_xx): + '''Calculation of chi_sq according to Text-NSP''' + (n_ix, n_xi) = n_ix_xi_tuple + n_oo=n_xx-n_ix-n_xi + + n_io=n_ix-n_ii + n_oi=n_xi-n_ii + n_oo=n_xx-n_ix-n_xi + + phi2=((n_ii*n_oo)-(n_io*n_io))**2/(n_xi*n_ix*(n_oi+n_oo)*(n_io+n_oo)) + self.chi_sqr=n_xx*phi2 + return(self.chi_sqr) + + def jaccard_TEXTNSP(self,n_ii, n_ix_xi_tuple, n_xx): + '''Calculation of Jaccard according to Text-NSP''' + (n_ix, n_xi) = n_ix_xi_tuple + n_oo=n_xx-n_ix-n_xi + + n_io=n_ix-n_ii + n_oi=n_xi-n_ii + n_oo=n_xx-n_ix-n_xi + + self.jaccard=n_ii/(n_ii+n_oi+n_io) + return(self.jaccard) + + def pmi_TEXTNSP(self,n_ii, n_ix_xi_tuple, n_xx): + '''Calculation of pmi according to Text-NSP''' + (n_ix, n_xi) = n_ix_xi_tuple + n_oo=n_xx-n_ix-n_xi + + n_io=n_ix-n_ii + n_oi=n_xi-n_ii + n_oo=n_xx-n_ix-n_xi + + m11=n_ix*n_xi/n_xx + self.PMI=math.log((n_ii/m11),2) + + return(self.PMI) + + def phi_sq_TEXTNSP(self,n_ii, n_ix_xi_tuple, n_xx): + '''Calculation of phi_sq according to Text-NSP''' + (n_ix, n_xi) = n_ix_xi_tuple + n_oo=n_xx-n_ix-n_xi + + n_io=n_ix-n_ii + n_oi=n_xi-n_ii + n_oo=n_xx-n_ix-n_xi + + self.phi2=((n_ii*n_oo)-(n_io*n_io))**2/(n_xi*n_ix*(n_oi+n_oo)*(n_io+n_oo)) + + return(self.phi2) + +class myTrigramAssocMeasures(nltk.collocations.TrigramAssocMeasures): + + def pmi_3g(cls, *dades): + n_iii=dades[0] + n_xxx=dades[3] + n_iix_tuple=dades[1] + n_ixx_tuple=dades[2] + (n_iix, n_ixi, n_xii) = n_iix_tuple + (n_ixx, n_xix, n_xxi) = n_ixx_tuple + n1pp=n_ixx+n_ixi+n_iix+n_iii + np1p=n_xix+n_xii+n_iix+n_iii + npp1=n_xxi+n_xii+n_xii+n_ixi+n_iii + n2pp=n_xxx+n_xxi+n_xix+n_xii + np2p=n_xxx+n_xxi+n_ixx+n_ixi + npp2=n_xxx+n_ixi+n_ixx+n_iix + + n111=n_iii + nppp=n_xxx + + m111=n1pp*np1p*npp1/(nppp*nppp) + PMI=math.log((n111/m111),2) + return(PMI) + + def poisson_stirling_3g(cls, *dades): + n_iii=dades[0] + n_xxx=dades[3] + n_iix_tuple=dades[1] + n_ixx_tuple=dades[2] + (n_iix, n_ixi, n_xii) = n_iix_tuple + (n_ixx, n_xix, n_xxi) = n_ixx_tuple + n1pp=n_ixx+n_ixi+n_iix+n_iii + np1p=n_xix+n_xii+n_iix+n_iii + npp1=n_xxi+n_xii+n_xii+n_ixi+n_iii + n2pp=n_xxx+n_xxi+n_xix+n_xii + np2p=n_xxx+n_xxi+n_ixx+n_ixi + npp2=n_xxx+n_ixi+n_ixx+n_iix + + n111=n_iii + nppp=n_xxx + + m111=n1pp*np1p*npp1/nppp + poisson_stirling=m111*(math.log(n111,2)-math.log(m111,2)-1) + return(poisson_stirling) + + def tmi_3g(cls, *dades): + n_iii=dades[0] + n_xxx=dades[3] + n_iix_tuple=dades[1] + n_ixx_tuple=dades[2] + (n_iix, n_ixi, n_xii) = n_iix_tuple + (n_ixx, n_xix, n_xxi) = n_ixx_tuple + n1pp=n_ixx+n_ixi+n_iix+n_iii + np1p=n_xix+n_xii+n_iix+n_iii + npp1=n_xxi+n_xii+n_xii+n_ixi+n_iii + n2pp=n_xxx+n_xxi+n_xix+n_xii + np2p=n_xxx+n_xxi+n_ixx+n_ixi + npp2=n_xxx+n_ixi+n_ixx+n_iix + + n111=n_iii + n112=n_iix + n121=n_ixi + n122=n_ixx + n211=n_xii + n212=n_xix + n221=n_xxi + n222=n_xxx + + nppp=n_xxx + m111=n1pp*np1p*npp1/nppp + m112=n1pp*np1p*npp2/nppp + m121=n1pp*np2p*npp1/nppp + m122=n1pp*np2p*npp2/nppp + m211=n2pp*np1p*npp1/nppp + m212=n2pp*np1p*npp2/nppp + m221=n2pp*np2p*npp1/nppp + m222=n2pp*np2p*npp2/nppp + try: + tmi = (n111/nppp * math.log((n111/m111),2) + n112/nppp * math.log((n112/m112),2) + n121/nppp * math.log((n121/m121),2) + n122/nppp * math.log((n122/m122),2) + n211/nppp * math.log((n211/m211),2) + n212/nppp * math.log((n212/m212),2) + n221/nppp * math.log((n221/m221),2) + n222/nppp * math.log((n222/m222),2)) + except: + tmi=0 + + return(tmi) + + + def loglikelihood_3g(cls, *dades): + n_iii=dades[0] + n_xxx=dades[3] + n_iix_tuple=dades[1] + n_ixx_tuple=dades[2] + (n_iix, n_ixi, n_xii) = n_iix_tuple + (n_ixx, n_xix, n_xxi) = n_ixx_tuple + n1pp=n_ixx+n_ixi+n_iix+n_iii + np1p=n_xix+n_xii+n_iix+n_iii + npp1=n_xxi+n_xii+n_xii+n_ixi+n_iii + n2pp=n_xxx+n_xxi+n_xix+n_xii + np2p=n_xxx+n_xxi+n_ixx+n_ixi + npp2=n_xxx+n_ixi+n_ixx+n_iix + + n111=n_iii + n112=n_iix + n121=n_ixi + n122=n_ixx + n211=n_xii + n212=n_xix + n221=n_xxi + n222=n_xxx + + nppp=n_xxx + m111=n1pp*np1p*npp1/nppp + m112=n1pp*np1p*npp2/nppp + m121=n1pp*np2p*npp1/nppp + m122=n1pp*np2p*npp2/nppp + m211=n2pp*np1p*npp1/nppp + m212=n2pp*np1p*npp2/nppp + m221=n2pp*np2p*npp1/nppp + m222=n2pp*np2p*npp2/nppp + try: + Log_Likelihood = 2 * (n111 * math.log((n111/m111),2) + n112 * math.log((n112/m112),2) + n121 * math.log((n121/m121),2) + n122 * math.log((n122/m122),2) + n211 * math.log((n211/m211),2) + n212 * math.log((n212/m212),2) + n221 * math.log((n221/m221),2) + n222 * math.log((n222/m222),2)) + except: + Log_Likelihood=0 + + return(Log_Likelihood) + + + diff --git a/gpl-3.0.txt b/gpl-3.0.txt new file mode 100644 index 0000000..f288702 --- /dev/null +++ b/gpl-3.0.txt @@ -0,0 +1,674 @@ + GNU GENERAL PUBLIC LICENSE + Version 3, 29 June 2007 + + Copyright (C) 2007 Free Software Foundation, Inc. <https://fsf.org/> + Everyone is permitted to copy and distribute verbatim copies + of this license document, but changing it is not allowed. + + Preamble + + The GNU General Public License is a free, copyleft license for +software and other kinds of works. + + The licenses for most software and other practical works are designed +to take away your freedom to share and change the works. By contrast, +the GNU General Public License is intended to guarantee your freedom to +share and change all versions of a program--to make sure it remains free +software for all its users. We, the Free Software Foundation, use the +GNU General Public License for most of our software; it applies also to +any other work released this way by its authors. You can apply it to +your programs, too. + + When we speak of free software, we are referring to freedom, not +price. Our General Public Licenses are designed to make sure that you +have the freedom to distribute copies of free software (and charge for +them if you wish), that you receive source code or can get it if you +want it, that you can change the software or use pieces of it in new +free programs, and that you know you can do these things. + + To protect your rights, we need to prevent others from denying you +these rights or asking you to surrender the rights. Therefore, you have +certain responsibilities if you distribute copies of the software, or if +you modify it: responsibilities to respect the freedom of others. + + For example, if you distribute copies of such a program, whether +gratis or for a fee, you must pass on to the recipients the same +freedoms that you received. You must make sure that they, too, receive +or can get the source code. And you must show them these terms so they +know their rights. + + Developers that use the GNU GPL protect your rights with two steps: +(1) assert copyright on the software, and (2) offer you this License +giving you legal permission to copy, distribute and/or modify it. + + For the developers' and authors' protection, the GPL clearly explains +that there is no warranty for this free software. For both users' and +authors' sake, the GPL requires that modified versions be marked as +changed, so that their problems will not be attributed erroneously to +authors of previous versions. + + Some devices are designed to deny users access to install or run +modified versions of the software inside them, although the manufacturer +can do so. This is fundamentally incompatible with the aim of +protecting users' freedom to change the software. The systematic +pattern of such abuse occurs in the area of products for individuals to +use, which is precisely where it is most unacceptable. Therefore, we +have designed this version of the GPL to prohibit the practice for those +products. If such problems arise substantially in other domains, we +stand ready to extend this provision to those domains in future versions +of the GPL, as needed to protect the freedom of users. + + Finally, every program is threatened constantly by software patents. +States should not allow patents to restrict development and use of +software on general-purpose computers, but in those that do, we wish to +avoid the special danger that patents applied to a free program could +make it effectively proprietary. To prevent this, the GPL assures that +patents cannot be used to render the program non-free. + + The precise terms and conditions for copying, distribution and +modification follow. + + TERMS AND CONDITIONS + + 0. Definitions. + + "This License" refers to version 3 of the GNU General Public License. + + "Copyright" also means copyright-like laws that apply to other kinds of +works, such as semiconductor masks. + + "The Program" refers to any copyrightable work licensed under this +License. Each licensee is addressed as "you". "Licensees" and +"recipients" may be individuals or organizations. + + To "modify" a work means to copy from or adapt all or part of the work +in a fashion requiring copyright permission, other than the making of an +exact copy. The resulting work is called a "modified version" of the +earlier work or a work "based on" the earlier work. + + A "covered work" means either the unmodified Program or a work based +on the Program. + + To "propagate" a work means to do anything with it that, without +permission, would make you directly or secondarily liable for +infringement under applicable copyright law, except executing it on a +computer or modifying a private copy. Propagation includes copying, +distribution (with or without modification), making available to the +public, and in some countries other activities as well. + + To "convey" a work means any kind of propagation that enables other +parties to make or receive copies. Mere interaction with a user through +a computer network, with no transfer of a copy, is not conveying. + + An interactive user interface displays "Appropriate Legal Notices" +to the extent that it includes a convenient and prominently visible +feature that (1) displays an appropriate copyright notice, and (2) +tells the user that there is no warranty for the work (except to the +extent that warranties are provided), that licensees may convey the +work under this License, and how to view a copy of this License. If +the interface presents a list of user commands or options, such as a +menu, a prominent item in the list meets this criterion. + + 1. Source Code. + + The "source code" for a work means the preferred form of the work +for making modifications to it. "Object code" means any non-source +form of a work. + + A "Standard Interface" means an interface that either is an official +standard defined by a recognized standards body, or, in the case of +interfaces specified for a particular programming language, one that +is widely used among developers working in that language. + + The "System Libraries" of an executable work include anything, other +than the work as a whole, that (a) is included in the normal form of +packaging a Major Component, but which is not part of that Major +Component, and (b) serves only to enable use of the work with that +Major Component, or to implement a Standard Interface for which an +implementation is available to the public in source code form. A +"Major Component", in this context, means a major essential component +(kernel, window system, and so on) of the specific operating system +(if any) on which the executable work runs, or a compiler used to +produce the work, or an object code interpreter used to run it. + + The "Corresponding Source" for a work in object code form means all +the source code needed to generate, install, and (for an executable +work) run the object code and to modify the work, including scripts to +control those activities. However, it does not include the work's +System Libraries, or general-purpose tools or generally available free +programs which are used unmodified in performing those activities but +which are not part of the work. For example, Corresponding Source +includes interface definition files associated with source files for +the work, and the source code for shared libraries and dynamically +linked subprograms that the work is specifically designed to require, +such as by intimate data communication or control flow between those +subprograms and other parts of the work. + + The Corresponding Source need not include anything that users +can regenerate automatically from other parts of the Corresponding +Source. + + The Corresponding Source for a work in source code form is that +same work. + + 2. Basic Permissions. + + All rights granted under this License are granted for the term of +copyright on the Program, and are irrevocable provided the stated +conditions are met. This License explicitly affirms your unlimited +permission to run the unmodified Program. The output from running a +covered work is covered by this License only if the output, given its +content, constitutes a covered work. This License acknowledges your +rights of fair use or other equivalent, as provided by copyright law. + + You may make, run and propagate covered works that you do not +convey, without conditions so long as your license otherwise remains +in force. You may convey covered works to others for the sole purpose +of having them make modifications exclusively for you, or provide you +with facilities for running those works, provided that you comply with +the terms of this License in conveying all material for which you do +not control copyright. Those thus making or running the covered works +for you must do so exclusively on your behalf, under your direction +and control, on terms that prohibit them from making any copies of +your copyrighted material outside their relationship with you. + + Conveying under any other circumstances is permitted solely under +the conditions stated below. Sublicensing is not allowed; section 10 +makes it unnecessary. + + 3. Protecting Users' Legal Rights From Anti-Circumvention Law. + + No covered work shall be deemed part of an effective technological +measure under any applicable law fulfilling obligations under article +11 of the WIPO copyright treaty adopted on 20 December 1996, or +similar laws prohibiting or restricting circumvention of such +measures. + + When you convey a covered work, you waive any legal power to forbid +circumvention of technological measures to the extent such circumvention +is effected by exercising rights under this License with respect to +the covered work, and you disclaim any intention to limit operation or +modification of the work as a means of enforcing, against the work's +users, your or third parties' legal rights to forbid circumvention of +technological measures. + + 4. Conveying Verbatim Copies. + + You may convey verbatim copies of the Program's source code as you +receive it, in any medium, provided that you conspicuously and +appropriately publish on each copy an appropriate copyright notice; +keep intact all notices stating that this License and any +non-permissive terms added in accord with section 7 apply to the code; +keep intact all notices of the absence of any warranty; and give all +recipients a copy of this License along with the Program. + + You may charge any price or no price for each copy that you convey, +and you may offer support or warranty protection for a fee. + + 5. Conveying Modified Source Versions. + + You may convey a work based on the Program, or the modifications to +produce it from the Program, in the form of source code under the +terms of section 4, provided that you also meet all of these conditions: + + a) The work must carry prominent notices stating that you modified + it, and giving a relevant date. + + b) The work must carry prominent notices stating that it is + released under this License and any conditions added under section + 7. This requirement modifies the requirement in section 4 to + "keep intact all notices". + + c) You must license the entire work, as a whole, under this + License to anyone who comes into possession of a copy. This + License will therefore apply, along with any applicable section 7 + additional terms, to the whole of the work, and all its parts, + regardless of how they are packaged. This License gives no + permission to license the work in any other way, but it does not + invalidate such permission if you have separately received it. + + d) If the work has interactive user interfaces, each must display + Appropriate Legal Notices; however, if the Program has interactive + interfaces that do not display Appropriate Legal Notices, your + work need not make them do so. + + A compilation of a covered work with other separate and independent +works, which are not by their nature extensions of the covered work, +and which are not combined with it such as to form a larger program, +in or on a volume of a storage or distribution medium, is called an +"aggregate" if the compilation and its resulting copyright are not +used to limit the access or legal rights of the compilation's users +beyond what the individual works permit. Inclusion of a covered work +in an aggregate does not cause this License to apply to the other +parts of the aggregate. + + 6. Conveying Non-Source Forms. + + You may convey a covered work in object code form under the terms +of sections 4 and 5, provided that you also convey the +machine-readable Corresponding Source under the terms of this License, +in one of these ways: + + a) Convey the object code in, or embodied in, a physical product + (including a physical distribution medium), accompanied by the + Corresponding Source fixed on a durable physical medium + customarily used for software interchange. + + b) Convey the object code in, or embodied in, a physical product + (including a physical distribution medium), accompanied by a + written offer, valid for at least three years and valid for as + long as you offer spare parts or customer support for that product + model, to give anyone who possesses the object code either (1) a + copy of the Corresponding Source for all the software in the + product that is covered by this License, on a durable physical + medium customarily used for software interchange, for a price no + more than your reasonable cost of physically performing this + conveying of source, or (2) access to copy the + Corresponding Source from a network server at no charge. + + c) Convey individual copies of the object code with a copy of the + written offer to provide the Corresponding Source. This + alternative is allowed only occasionally and noncommercially, and + only if you received the object code with such an offer, in accord + with subsection 6b. + + d) Convey the object code by offering access from a designated + place (gratis or for a charge), and offer equivalent access to the + Corresponding Source in the same way through the same place at no + further charge. You need not require recipients to copy the + Corresponding Source along with the object code. If the place to + copy the object code is a network server, the Corresponding Source + may be on a different server (operated by you or a third party) + that supports equivalent copying facilities, provided you maintain + clear directions next to the object code saying where to find the + Corresponding Source. Regardless of what server hosts the + Corresponding Source, you remain obligated to ensure that it is + available for as long as needed to satisfy these requirements. + + e) Convey the object code using peer-to-peer transmission, provided + you inform other peers where the object code and Corresponding + Source of the work are being offered to the general public at no + charge under subsection 6d. + + A separable portion of the object code, whose source code is excluded +from the Corresponding Source as a System Library, need not be +included in conveying the object code work. + + A "User Product" is either (1) a "consumer product", which means any +tangible personal property which is normally used for personal, family, +or household purposes, or (2) anything designed or sold for incorporation +into a dwelling. In determining whether a product is a consumer product, +doubtful cases shall be resolved in favor of coverage. For a particular +product received by a particular user, "normally used" refers to a +typical or common use of that class of product, regardless of the status +of the particular user or of the way in which the particular user +actually uses, or expects or is expected to use, the product. A product +is a consumer product regardless of whether the product has substantial +commercial, industrial or non-consumer uses, unless such uses represent +the only significant mode of use of the product. + + "Installation Information" for a User Product means any methods, +procedures, authorization keys, or other information required to install +and execute modified versions of a covered work in that User Product from +a modified version of its Corresponding Source. The information must +suffice to ensure that the continued functioning of the modified object +code is in no case prevented or interfered with solely because +modification has been made. + + If you convey an object code work under this section in, or with, or +specifically for use in, a User Product, and the conveying occurs as +part of a transaction in which the right of possession and use of the +User Product is transferred to the recipient in perpetuity or for a +fixed term (regardless of how the transaction is characterized), the +Corresponding Source conveyed under this section must be accompanied +by the Installation Information. But this requirement does not apply +if neither you nor any third party retains the ability to install +modified object code on the User Product (for example, the work has +been installed in ROM). + + The requirement to provide Installation Information does not include a +requirement to continue to provide support service, warranty, or updates +for a work that has been modified or installed by the recipient, or for +the User Product in which it has been modified or installed. Access to a +network may be denied when the modification itself materially and +adversely affects the operation of the network or violates the rules and +protocols for communication across the network. + + Corresponding Source conveyed, and Installation Information provided, +in accord with this section must be in a format that is publicly +documented (and with an implementation available to the public in +source code form), and must require no special password or key for +unpacking, reading or copying. + + 7. Additional Terms. + + "Additional permissions" are terms that supplement the terms of this +License by making exceptions from one or more of its conditions. +Additional permissions that are applicable to the entire Program shall +be treated as though they were included in this License, to the extent +that they are valid under applicable law. If additional permissions +apply only to part of the Program, that part may be used separately +under those permissions, but the entire Program remains governed by +this License without regard to the additional permissions. + + When you convey a copy of a covered work, you may at your option +remove any additional permissions from that copy, or from any part of +it. (Additional permissions may be written to require their own +removal in certain cases when you modify the work.) You may place +additional permissions on material, added by you to a covered work, +for which you have or can give appropriate copyright permission. + + Notwithstanding any other provision of this License, for material you +add to a covered work, you may (if authorized by the copyright holders of +that material) supplement the terms of this License with terms: + + a) Disclaiming warranty or limiting liability differently from the + terms of sections 15 and 16 of this License; or + + b) Requiring preservation of specified reasonable legal notices or + author attributions in that material or in the Appropriate Legal + Notices displayed by works containing it; or + + c) Prohibiting misrepresentation of the origin of that material, or + requiring that modified versions of such material be marked in + reasonable ways as different from the original version; or + + d) Limiting the use for publicity purposes of names of licensors or + authors of the material; or + + e) Declining to grant rights under trademark law for use of some + trade names, trademarks, or service marks; or + + f) Requiring indemnification of licensors and authors of that + material by anyone who conveys the material (or modified versions of + it) with contractual assumptions of liability to the recipient, for + any liability that these contractual assumptions directly impose on + those licensors and authors. + + All other non-permissive additional terms are considered "further +restrictions" within the meaning of section 10. If the Program as you +received it, or any part of it, contains a notice stating that it is +governed by this License along with a term that is a further +restriction, you may remove that term. If a license document contains +a further restriction but permits relicensing or conveying under this +License, you may add to a covered work material governed by the terms +of that license document, provided that the further restriction does +not survive such relicensing or conveying. + + If you add terms to a covered work in accord with this section, you +must place, in the relevant source files, a statement of the +additional terms that apply to those files, or a notice indicating +where to find the applicable terms. + + Additional terms, permissive or non-permissive, may be stated in the +form of a separately written license, or stated as exceptions; +the above requirements apply either way. + + 8. Termination. + + You may not propagate or modify a covered work except as expressly +provided under this License. Any attempt otherwise to propagate or +modify it is void, and will automatically terminate your rights under +this License (including any patent licenses granted under the third +paragraph of section 11). + + However, if you cease all violation of this License, then your +license from a particular copyright holder is reinstated (a) +provisionally, unless and until the copyright holder explicitly and +finally terminates your license, and (b) permanently, if the copyright +holder fails to notify you of the violation by some reasonable means +prior to 60 days after the cessation. + + Moreover, your license from a particular copyright holder is +reinstated permanently if the copyright holder notifies you of the +violation by some reasonable means, this is the first time you have +received notice of violation of this License (for any work) from that +copyright holder, and you cure the violation prior to 30 days after +your receipt of the notice. + + Termination of your rights under this section does not terminate the +licenses of parties who have received copies or rights from you under +this License. If your rights have been terminated and not permanently +reinstated, you do not qualify to receive new licenses for the same +material under section 10. + + 9. Acceptance Not Required for Having Copies. + + You are not required to accept this License in order to receive or +run a copy of the Program. Ancillary propagation of a covered work +occurring solely as a consequence of using peer-to-peer transmission +to receive a copy likewise does not require acceptance. However, +nothing other than this License grants you permission to propagate or +modify any covered work. These actions infringe copyright if you do +not accept this License. Therefore, by modifying or propagating a +covered work, you indicate your acceptance of this License to do so. + + 10. Automatic Licensing of Downstream Recipients. + + Each time you convey a covered work, the recipient automatically +receives a license from the original licensors, to run, modify and +propagate that work, subject to this License. You are not responsible +for enforcing compliance by third parties with this License. + + An "entity transaction" is a transaction transferring control of an +organization, or substantially all assets of one, or subdividing an +organization, or merging organizations. If propagation of a covered +work results from an entity transaction, each party to that +transaction who receives a copy of the work also receives whatever +licenses to the work the party's predecessor in interest had or could +give under the previous paragraph, plus a right to possession of the +Corresponding Source of the work from the predecessor in interest, if +the predecessor has it or can get it with reasonable efforts. + + You may not impose any further restrictions on the exercise of the +rights granted or affirmed under this License. For example, you may +not impose a license fee, royalty, or other charge for exercise of +rights granted under this License, and you may not initiate litigation +(including a cross-claim or counterclaim in a lawsuit) alleging that +any patent claim is infringed by making, using, selling, offering for +sale, or importing the Program or any portion of it. + + 11. Patents. + + A "contributor" is a copyright holder who authorizes use under this +License of the Program or a work on which the Program is based. The +work thus licensed is called the contributor's "contributor version". + + A contributor's "essential patent claims" are all patent claims +owned or controlled by the contributor, whether already acquired or +hereafter acquired, that would be infringed by some manner, permitted +by this License, of making, using, or selling its contributor version, +but do not include claims that would be infringed only as a +consequence of further modification of the contributor version. For +purposes of this definition, "control" includes the right to grant +patent sublicenses in a manner consistent with the requirements of +this License. + + Each contributor grants you a non-exclusive, worldwide, royalty-free +patent license under the contributor's essential patent claims, to +make, use, sell, offer for sale, import and otherwise run, modify and +propagate the contents of its contributor version. + + In the following three paragraphs, a "patent license" is any express +agreement or commitment, however denominated, not to enforce a patent +(such as an express permission to practice a patent or covenant not to +sue for patent infringement). To "grant" such a patent license to a +party means to make such an agreement or commitment not to enforce a +patent against the party. + + If you convey a covered work, knowingly relying on a patent license, +and the Corresponding Source of the work is not available for anyone +to copy, free of charge and under the terms of this License, through a +publicly available network server or other readily accessible means, +then you must either (1) cause the Corresponding Source to be so +available, or (2) arrange to deprive yourself of the benefit of the +patent license for this particular work, or (3) arrange, in a manner +consistent with the requirements of this License, to extend the patent +license to downstream recipients. "Knowingly relying" means you have +actual knowledge that, but for the patent license, your conveying the +covered work in a country, or your recipient's use of the covered work +in a country, would infringe one or more identifiable patents in that +country that you have reason to believe are valid. + + If, pursuant to or in connection with a single transaction or +arrangement, you convey, or propagate by procuring conveyance of, a +covered work, and grant a patent license to some of the parties +receiving the covered work authorizing them to use, propagate, modify +or convey a specific copy of the covered work, then the patent license +you grant is automatically extended to all recipients of the covered +work and works based on it. + + A patent license is "discriminatory" if it does not include within +the scope of its coverage, prohibits the exercise of, or is +conditioned on the non-exercise of one or more of the rights that are +specifically granted under this License. You may not convey a covered +work if you are a party to an arrangement with a third party that is +in the business of distributing software, under which you make payment +to the third party based on the extent of your activity of conveying +the work, and under which the third party grants, to any of the +parties who would receive the covered work from you, a discriminatory +patent license (a) in connection with copies of the covered work +conveyed by you (or copies made from those copies), or (b) primarily +for and in connection with specific products or compilations that +contain the covered work, unless you entered into that arrangement, +or that patent license was granted, prior to 28 March 2007. + + Nothing in this License shall be construed as excluding or limiting +any implied license or other defenses to infringement that may +otherwise be available to you under applicable patent law. + + 12. No Surrender of Others' Freedom. + + If conditions are imposed on you (whether by court order, agreement or +otherwise) that contradict the conditions of this License, they do not +excuse you from the conditions of this License. If you cannot convey a +covered work so as to satisfy simultaneously your obligations under this +License and any other pertinent obligations, then as a consequence you may +not convey it at all. For example, if you agree to terms that obligate you +to collect a royalty for further conveying from those to whom you convey +the Program, the only way you could satisfy both those terms and this +License would be to refrain entirely from conveying the Program. + + 13. Use with the GNU Affero General Public License. + + Notwithstanding any other provision of this License, you have +permission to link or combine any covered work with a work licensed +under version 3 of the GNU Affero General Public License into a single +combined work, and to convey the resulting work. The terms of this +License will continue to apply to the part which is the covered work, +but the special requirements of the GNU Affero General Public License, +section 13, concerning interaction through a network will apply to the +combination as such. + + 14. Revised Versions of this License. + + The Free Software Foundation may publish revised and/or new versions of +the GNU General Public License from time to time. Such new versions will +be similar in spirit to the present version, but may differ in detail to +address new problems or concerns. + + Each version is given a distinguishing version number. If the +Program specifies that a certain numbered version of the GNU General +Public License "or any later version" applies to it, you have the +option of following the terms and conditions either of that numbered +version or of any later version published by the Free Software +Foundation. If the Program does not specify a version number of the +GNU General Public License, you may choose any version ever published +by the Free Software Foundation. + + If the Program specifies that a proxy can decide which future +versions of the GNU General Public License can be used, that proxy's +public statement of acceptance of a version permanently authorizes you +to choose that version for the Program. + + Later license versions may give you additional or different +permissions. However, no additional obligations are imposed on any +author or copyright holder as a result of your choosing to follow a +later version. + + 15. Disclaimer of Warranty. + + THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY +APPLICABLE LAW. EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT +HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY +OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, +THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR +PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM +IS WITH YOU. SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF +ALL NECESSARY SERVICING, REPAIR OR CORRECTION. + + 16. Limitation of Liability. + + IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING +WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS +THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY +GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE +USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF +DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD +PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS), +EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF +SUCH DAMAGES. + + 17. Interpretation of Sections 15 and 16. + + If the disclaimer of warranty and limitation of liability provided +above cannot be given local legal effect according to their terms, +reviewing courts shall apply local law that most closely approximates +an absolute waiver of all civil liability in connection with the +Program, unless a warranty or assumption of liability accompanies a +copy of the Program in return for a fee. + + END OF TERMS AND CONDITIONS + + How to Apply These Terms to Your New Programs + + If you develop a new program, and you want it to be of the greatest +possible use to the public, the best way to achieve this is to make it +free software which everyone can redistribute and change under these terms. + + To do so, attach the following notices to the program. It is safest +to attach them to the start of each source file to most effectively +state the exclusion of warranty; and each file should have at least +the "copyright" line and a pointer to where the full notice is found. + + <one line to give the program's name and a brief idea of what it does.> + Copyright (C) <year> <name of author> + + This program is free software: you can redistribute it and/or modify + it under the terms of the GNU General Public License as published by + the Free Software Foundation, either version 3 of the License, or + (at your option) any later version. + + This program is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + GNU General Public License for more details. + + You should have received a copy of the GNU General Public License + along with this program. If not, see <https://www.gnu.org/licenses/>. + +Also add information on how to contact you by electronic and paper mail. + + If the program does terminal interaction, make it output a short +notice like this when it starts in an interactive mode: + + <program> Copyright (C) <year> <name of author> + This program comes with ABSOLUTELY NO WARRANTY; for details type `show w'. + This is free software, and you are welcome to redistribute it + under certain conditions; type `show c' for details. + +The hypothetical commands `show w' and `show c' should show the appropriate +parts of the General Public License. Of course, your program's commands +might be different; for a GUI interface, you would use an "about box". + + You should also get your employer (if you work as a programmer) or school, +if any, to sign a "copyright disclaimer" for the program, if necessary. +For more information on this, and how to apply and follow the GNU GPL, see +<https://www.gnu.org/licenses/>. + + The GNU General Public License does not permit incorporating your program +into proprietary programs. If your program is a subroutine library, you +may consider it more useful to permit linking proprietary applications with +the library. If this is what you want to do, use the GNU Lesser General +Public License instead of this License. But first, please read +<https://www.gnu.org/licenses/why-not-lgpl.html>. |