diff --git a/doc/classes/RIR.html b/doc/classes/RIR.html
index 77d50d4..0149a10 100644
--- a/doc/classes/RIR.html
+++ b/doc/classes/RIR.html
@@ -63,6 +63,16 @@
+
+
+ lib/rir/corpus.rb
+
+
+
+
+
+
+
lib/rir/query.rb
@@ -73,6 +83,16 @@
+
+
+ lib/rir/string.rb
+
+
+
+
+
+
+
lib/rir/document.rb
@@ -142,6 +162,52 @@ with this program. If not, see <www.gnu.org/licenses/>.
+This file is a part of an Information Retrieval oriented Ruby library +
+
+Copyright (C) 2010-2011 Romain Deveaud
+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 <www.gnu.org/licenses/>. +
++This file is a part of an Information Retrieval oriented Ruby library +
+
+Copyright (C) 2010-2011 Romain Deveaud
+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 <www.gnu.org/licenses/>. +
+General module for many purposes related to Information Retrieval.
@@ -161,6 +227,7 @@ General module for many purposes related to Information Retrieval. Module RIR::IndriStoplist | += | +[ "a", "anything", "anyway", "anywhere", "apart", "are", "around", "as", "at", "av", "be", "became", "because", "become", "becomes", "becoming", "been", "before", "beforehand", "behind", "being", "below", "beside", "besides", "between", "beyond", "both", "but", "by", "can", "cannot", "canst", "certain", "cf", "choose", "contrariwise", "cos", "could", "cu", "day", "do", "does", "doesn't", "doing", "dost", "doth", "double", "down", "dual", "during", "each", "either", "else", "elsewhere", "enough", "et", "etc", "even", "ever", "every", "everybody", "everyone", "everything", "everywhere", "except", "excepted", "excepting", "exception", "exclude", "excluding", "exclusive", "far", "farther", "farthest", "few", "ff", "first", "for", "formerly", "forth", "forward", "from", "front", "further", "furthermore", "furthest", "get", "go", "had", "halves", "hardly", "has", "hast", "hath", "have", "he", "hence", "henceforth", "her", "here", "hereabouts", "hereafter", "hereby", "herein", "hereto", "hereupon", "hers", "herself", "him", "himself", "hindmost", "his", "hither", "hitherto", "how", "however", "howsoever", "i", "ie", "if", "in", "inasmuch", "inc", "include", "included", "including", "indeed", "indoors", "inside", "insomuch", "instead", "into", "inward", "inwards", "is", "it", "its", "itself", "just", "kind", "kg", "km", "last", "latter", "latterly", "less", "lest", "let", "like", "little", "ltd", "many", "may", "maybe", "me", "meantime", "meanwhile", "might", "moreover", "most", "mostly", "more", "mr", "mrs", "ms", "much", "must", "my", "myself", "namely", "need", "neither", "never", "nevertheless", "next", "no", "nobody", "none", "nonetheless", "noone", "nope", "nor", "not", "nothing", "notwithstanding", "now", "nowadays", "nowhere", "of", "off", "often", "ok", "on", "once", "one", "only", "onto", "or", "other", "others", "otherwise", "ought", "our", "ours", "ourselves", "out", "outside", "over", "own", "per", "perhaps", "plenty", "provide", "quite", "rather", "really", "round", "said", "sake", "same", "sang", "save", "saw", "see", "seeing", "seem", "seemed", "seeming", "seems", "seen", "seldom", "selves", "sent", "several", "shalt", "she", "should", "shown", "sideways", "since", "slept", "slew", "slung", "slunk", "smote", "so", "some", "somebody", "somehow", "someone", "something", "sometime", "sometimes", "somewhat", "somewhere", "spake", "spat", "spoke", "spoken", "sprang", "sprung", "stave", "staves", "still", "such", "supposing", "than", "that", "the", "thee", "their", "them", "themselves", "then", "thence", "thenceforth", "there", "thereabout", "thereabouts", "thereafter", "thereby", "therefore", "therein", "thereof", "thereon", "thereto", "thereupon", "these", "they", "this", "those", "thou", "though", "thrice", "through", "throughout", "thru", "thus", "thy", "thyself", "till", "to", "together", "too", "toward", "towards", "ugh", "unable", "under", "underneath", "unless", "unlike", "until", "up", "upon", "upward", "upwards", "us", "use", "used", "using", "very", "via", "vs", "want", "was", "we", "week", "well", "were", "what", "whatever", "whatsoever", "when", "whence", "whenever", "whensoever", "where", "whereabouts", "whereafter", "whereas", "whereat", "whereby", "wherefore", "wherefrom", "wherein", "whereinto", "whereof", "whereon", "wheresoever", "whereto", "whereunto", "whereupon", "wherever", "wherewith", "whether", "whew", "which", "whichever", "whichsoever", "while", "whilst", "whither", "who", "whoa", "whoever", "whole", "whom", "whomever", "whomsoever", "whose", "whosoever", "why", "will", "wilt", "with", "within", "without", "worse", "worst", "would", "wow", "ye", "yet", "year", "yippee", "you", "your", "yours", "yourself", "yourselves" ] | + ++ | +These are the default stopwords provided by Lemur. + + | + +
# File lib/rir/corpus.rb, line 25 - def initialize(path) - @path = path.chomp "/" - end- - diff --git a/doc/classes/RIR/Corpus.src/M000017.html b/doc/classes/RIR/Corpus.src/M000017.html deleted file mode 100644 index a4eb5fa..0000000 --- a/doc/classes/RIR/Corpus.src/M000017.html +++ /dev/null @@ -1,15 +0,0 @@ - - - -
# File lib/rir/corpus.rb, line 35 - def files - Dir["#{@path}/**/*.*"] - end- - diff --git a/doc/classes/RIR/Corpus.src/M000018.html b/doc/classes/RIR/Corpus.src/M000018.html deleted file mode 100644 index 2ebdcfd..0000000 --- a/doc/classes/RIR/Corpus.src/M000018.html +++ /dev/null @@ -1,15 +0,0 @@ - - - -
# File lib/rir/corpus.rb, line 36 - def files - Dir["#{@path}/**/*.*"] - end- - diff --git a/doc/classes/RIR/Corpus.src/M000020.html b/doc/classes/RIR/Corpus.src/M000020.html new file mode 100644 index 0000000..cb605ef --- /dev/null +++ b/doc/classes/RIR/Corpus.src/M000020.html @@ -0,0 +1,15 @@ + + + +
# File lib/rir/corpus.rb, line 25 + def initialize(path) + @path = path.chomp "/" + end+ + diff --git a/doc/classes/RIR/Corpus.src/M000021.html b/doc/classes/RIR/Corpus.src/M000021.html new file mode 100644 index 0000000..a4eb5fa --- /dev/null +++ b/doc/classes/RIR/Corpus.src/M000021.html @@ -0,0 +1,15 @@ + + + +
# File lib/rir/corpus.rb, line 35 + def files + Dir["#{@path}/**/*.*"] + end+ + diff --git a/doc/classes/RIR/Document.html b/doc/classes/RIR/Document.html index 00f66b4..fdefaa1 100644 --- a/doc/classes/RIR/Document.html +++ b/doc/classes/RIR/Document.html @@ -99,17 +99,17 @@ from a string.
# File lib/rir/document.rb, line 31 - def format_words - wo = [] - - @doc_content.split.each do |w| - w.split(/\W/).each do |sw| - wo.push(sw.downcase) if sw =~ /[a-zA-Z]/ - end - end - - wo - end- - diff --git a/doc/classes/RIR/Document.src/M000009.html b/doc/classes/RIR/Document.src/M000009.html deleted file mode 100644 index 6257629..0000000 --- a/doc/classes/RIR/Document.src/M000009.html +++ /dev/null @@ -1,26 +0,0 @@ - - - -
# File lib/rir/document.rb, line 46 - def ngrams(n) - window = [] - ngrams_array = [] - - @words.each do |w| - window.push(w) - if window.size == n - ngrams_array.push window.join(" ") - window.delete_at(0) - end - end - - ngrams_array.uniq - end- - diff --git a/doc/classes/RIR/Document.src/M000010.html b/doc/classes/RIR/Document.src/M000010.html deleted file mode 100644 index e8ddeec..0000000 --- a/doc/classes/RIR/Document.src/M000010.html +++ /dev/null @@ -1,18 +0,0 @@ - - - -
# File lib/rir/document.rb, line 64 - def count_words - counts = Hash.new { |h,k| h[k] = 0 } - @words.each { |w| counts[w] += 1 } - - counts - end- - diff --git a/doc/classes/RIR/Document.src/M000011.html b/doc/classes/RIR/Document.src/M000011.html deleted file mode 100644 index 50f6db7..0000000 --- a/doc/classes/RIR/Document.src/M000011.html +++ /dev/null @@ -1,24 +0,0 @@ - - - -
# File lib/rir/document.rb, line 78 - def entropy(s) - en = 0.0 - counts = self.count_words - - s.split.each do |w| - p_wi = counts[w].to_f/@words.count.to_f - en += p_wi*Math.log2(p_wi) - end - - en *= -1 - en - end- - diff --git a/doc/classes/RIR/Document.src/M000012.html b/doc/classes/RIR/Document.src/M000012.html deleted file mode 100644 index eb4436b..0000000 --- a/doc/classes/RIR/Document.src/M000012.html +++ /dev/null @@ -1,15 +0,0 @@ - - - -
# File lib/rir/document.rb, line 94 - def tf(s) - self.count_words[s].to_f/@words.size.to_f - end- - diff --git a/doc/classes/RIR/Document.src/M000013.html b/doc/classes/RIR/Document.src/M000013.html deleted file mode 100644 index 1ef96d5..0000000 --- a/doc/classes/RIR/Document.src/M000013.html +++ /dev/null @@ -1,16 +0,0 @@ - - - -
# File lib/rir/document.rb, line 99 - def initialize(content) - @doc_content = content - @words = format_words - end- - diff --git a/doc/classes/RIR/Document.src/M000014.html b/doc/classes/RIR/Document.src/M000014.html deleted file mode 100644 index b882fcd..0000000 --- a/doc/classes/RIR/Document.src/M000014.html +++ /dev/null @@ -1,16 +0,0 @@ - - - -
# File lib/rir/document.rb, line 92 - def initialize(content) - @doc_content = content - @words = format_words - end- - diff --git a/doc/classes/RIR/Document.src/M000019.html b/doc/classes/RIR/Document.src/M000019.html deleted file mode 100644 index 72c51f5..0000000 --- a/doc/classes/RIR/Document.src/M000019.html +++ /dev/null @@ -1,23 +0,0 @@ - - - -
# File lib/rir/document.rb, line 31 - def format_words - wo = [] - - @doc_content.split.each do |w| - w.split(/\W/).each do |sw| - wo.push(sw.downcase) if sw =~ /[a-zA-Z]/ - end - end - - wo - end- - diff --git a/doc/classes/RIR/Document.src/M000020.html b/doc/classes/RIR/Document.src/M000020.html deleted file mode 100644 index 6257629..0000000 --- a/doc/classes/RIR/Document.src/M000020.html +++ /dev/null @@ -1,26 +0,0 @@ - - - -
# File lib/rir/document.rb, line 46 - def ngrams(n) - window = [] - ngrams_array = [] - - @words.each do |w| - window.push(w) - if window.size == n - ngrams_array.push window.join(" ") - window.delete_at(0) - end - end - - ngrams_array.uniq - end- - diff --git a/doc/classes/RIR/Document.src/M000021.html b/doc/classes/RIR/Document.src/M000021.html deleted file mode 100644 index e8ddeec..0000000 --- a/doc/classes/RIR/Document.src/M000021.html +++ /dev/null @@ -1,18 +0,0 @@ - - - -
# File lib/rir/document.rb, line 64 - def count_words - counts = Hash.new { |h,k| h[k] = 0 } - @words.each { |w| counts[w] += 1 } - - counts - end- - diff --git a/doc/classes/RIR/Document.src/M000022.html b/doc/classes/RIR/Document.src/M000022.html index 5694971..72c51f5 100644 --- a/doc/classes/RIR/Document.src/M000022.html +++ b/doc/classes/RIR/Document.src/M000022.html @@ -2,23 +2,22 @@ "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd"> -
# File lib/rir/document.rb, line 77 - def entropy(s) - en = 0.0 - counts = self.count_words +# File lib/rir/document.rb, line 31 + def format_words + wo = [] - s.split.each do |w| - p_wi = counts[w].to_f/@words.count.to_f - en += p_wi*Math.log2(p_wi) + @doc_content.split.each do |w| + w.split(/\W/).each do |sw| + wo.push(sw.downcase) if sw =~ /[a-zA-Z]/ + end end - - en *= -1 - en + + wo enddiff --git a/doc/classes/RIR/Document.src/M000023.html b/doc/classes/RIR/Document.src/M000023.html index b882fcd..6257629 100644 --- a/doc/classes/RIR/Document.src/M000023.html +++ b/doc/classes/RIR/Document.src/M000023.html @@ -2,15 +2,25 @@ "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd"> -new (RIR::Document) +ngrams (RIR::Document) -# File lib/rir/document.rb, line 92 - def initialize(content) - @doc_content = content - @words = format_words +# File lib/rir/document.rb, line 46 + def ngrams(n) + window = [] + ngrams_array = [] + + @words.each do |w| + window.push(w) + if window.size == n + ngrams_array.push window.join(" ") + window.delete_at(0) + end + end + + ngrams_array.uniq enddiff --git a/doc/classes/RIR/Document.src/M000024.html b/doc/classes/RIR/Document.src/M000024.html new file mode 100644 index 0000000..e8ddeec --- /dev/null +++ b/doc/classes/RIR/Document.src/M000024.html @@ -0,0 +1,18 @@ + + + +count_words (RIR::Document) + + + + +# File lib/rir/document.rb, line 64 + def count_words + counts = Hash.new { |h,k| h[k] = 0 } + @words.each { |w| counts[w] += 1 } + + counts + end+ + diff --git a/doc/classes/RIR/Document.src/M000025.html b/doc/classes/RIR/Document.src/M000025.html new file mode 100644 index 0000000..50f6db7 --- /dev/null +++ b/doc/classes/RIR/Document.src/M000025.html @@ -0,0 +1,24 @@ + + + +entropy (RIR::Document) + + + + +# File lib/rir/document.rb, line 78 + def entropy(s) + en = 0.0 + counts = self.count_words + + s.split.each do |w| + p_wi = counts[w].to_f/@words.count.to_f + en += p_wi*Math.log2(p_wi) + end + + en *= -1 + en + end+ + diff --git a/doc/classes/RIR/Document.src/M000026.html b/doc/classes/RIR/Document.src/M000026.html new file mode 100644 index 0000000..eb4436b --- /dev/null +++ b/doc/classes/RIR/Document.src/M000026.html @@ -0,0 +1,15 @@ + + + +tf (RIR::Document) + + + + +# File lib/rir/document.rb, line 94 + def tf(s) + self.count_words[s].to_f/@words.size.to_f + end+ + diff --git a/doc/classes/RIR/Document.src/M000027.html b/doc/classes/RIR/Document.src/M000027.html new file mode 100644 index 0000000..1ef96d5 --- /dev/null +++ b/doc/classes/RIR/Document.src/M000027.html @@ -0,0 +1,16 @@ + + + +new (RIR::Document) + + + + +# File lib/rir/document.rb, line 99 + def initialize(content) + @doc_content = content + @words = format_words + end+ + diff --git a/doc/classes/RIR/Indri/IndriQuery.html b/doc/classes/RIR/Indri/IndriQuery.html index 922525d..02ba68c 100644 --- a/doc/classes/RIR/Indri/IndriQuery.html +++ b/doc/classes/RIR/Indri/IndriQuery.html @@ -95,9 +95,9 @@
# File lib/rir/query.rb, line 62 - def initialize(id,query,params) - @params = params - # Here we set the default retrieval model as Language Modeling - # with a Dirichlet smoothing at 2500. - # TODO: maybe a Rule class... - @params.rule = 'method:dirichlet,mu:2500' if @params.rule.nil? - - @id = id - @query = query - end- - diff --git a/doc/classes/RIR/Indri/IndriQuery.src/M000007.html b/doc/classes/RIR/Indri/IndriQuery.src/M000007.html deleted file mode 100644 index e237f9a..0000000 --- a/doc/classes/RIR/Indri/IndriQuery.src/M000007.html +++ /dev/null @@ -1,22 +0,0 @@ - - - -
# File lib/rir/query.rb, line 73 - def to_s - h = @params.to_s - h += "<query>\n" - h += "<number>#{@id}</number>\n" - h += "<text>#{@query}</text>\n" - h += "</query>\n" - h += "</parameters>" - - h - end- - diff --git a/doc/classes/RIR/Indri/IndriQuery.src/M000014.html b/doc/classes/RIR/Indri/IndriQuery.src/M000014.html deleted file mode 100644 index c72d135..0000000 --- a/doc/classes/RIR/Indri/IndriQuery.src/M000014.html +++ /dev/null @@ -1,22 +0,0 @@ - - - -
# File lib/rir/query.rb, line 62 - def initialize(id,query,params) - @params = params - # Here we set the default retrieval model as Language Modeling - # with a Dirichlet smoothing at 2500. - # TODO: maybe a Rule class... - @params.rule = 'method:dirichlet,mu:2500' if @params.rule.nil? - - @id = id - @query = query - end- - diff --git a/doc/classes/RIR/Indri/IndriQuery.src/M000015.html b/doc/classes/RIR/Indri/IndriQuery.src/M000015.html deleted file mode 100644 index e237f9a..0000000 --- a/doc/classes/RIR/Indri/IndriQuery.src/M000015.html +++ /dev/null @@ -1,22 +0,0 @@ - - - -
# File lib/rir/query.rb, line 73 - def to_s - h = @params.to_s - h += "<query>\n" - h += "<number>#{@id}</number>\n" - h += "<text>#{@query}</text>\n" - h += "</query>\n" - h += "</parameters>" - - h - end- - diff --git a/doc/classes/RIR/Indri/IndriQuery.src/M000016.html b/doc/classes/RIR/Indri/IndriQuery.src/M000016.html deleted file mode 100644 index 515e431..0000000 --- a/doc/classes/RIR/Indri/IndriQuery.src/M000016.html +++ /dev/null @@ -1,22 +0,0 @@ - - - -
# File lib/rir/query.rb, line 74 - def to_s - h = @params.to_s - h += "<query>\n" - h += "<number>#{@id}</number>\n" - h += "<text>#{@query}</text>\n" - h += "</query>\n" - h += "</parameters>" - - h - end- - diff --git a/doc/classes/RIR/Indri/IndriQuery.src/M000018.html b/doc/classes/RIR/Indri/IndriQuery.src/M000018.html new file mode 100644 index 0000000..c72d135 --- /dev/null +++ b/doc/classes/RIR/Indri/IndriQuery.src/M000018.html @@ -0,0 +1,22 @@ + + + +
# File lib/rir/query.rb, line 62 + def initialize(id,query,params) + @params = params + # Here we set the default retrieval model as Language Modeling + # with a Dirichlet smoothing at 2500. + # TODO: maybe a Rule class... + @params.rule = 'method:dirichlet,mu:2500' if @params.rule.nil? + + @id = id + @query = query + end+ + diff --git a/doc/classes/RIR/Indri/IndriQuery.src/M000019.html b/doc/classes/RIR/Indri/IndriQuery.src/M000019.html new file mode 100644 index 0000000..e237f9a --- /dev/null +++ b/doc/classes/RIR/Indri/IndriQuery.src/M000019.html @@ -0,0 +1,22 @@ + + + +
# File lib/rir/query.rb, line 73 + def to_s + h = @params.to_s + h += "<query>\n" + h += "<number>#{@id}</number>\n" + h += "<text>#{@query}</text>\n" + h += "</query>\n" + h += "</parameters>" + + h + end+ + diff --git a/doc/classes/RIR/Indri/Parameters.html b/doc/classes/RIR/Indri/Parameters.html index 28e11cb..79d6734 100644 --- a/doc/classes/RIR/Indri/Parameters.html +++ b/doc/classes/RIR/Indri/Parameters.html @@ -91,9 +91,9 @@
# File lib/rir/query.rb, line 30 - def initialize(corpus,mem="1g",count="1000",offset="1",run_id="default",print_query=false,print_docs=false) - @index_path = corpus - @memory = mem - @count = count - @offset = offset - @run_id = run_id - @print_query = print_query ? "true" : "false" - @print_docs = print_docs ? "true" : "false" - end- - diff --git a/doc/classes/RIR/Indri/Parameters.src/M000005.html b/doc/classes/RIR/Indri/Parameters.src/M000005.html deleted file mode 100644 index 3a235ca..0000000 --- a/doc/classes/RIR/Indri/Parameters.src/M000005.html +++ /dev/null @@ -1,29 +0,0 @@ - - - -
# File lib/rir/query.rb, line 40 - def to_s - h = "<parameters>\n" - h += "<memory>#{@memory}</memory>\n" - h += "<index>#{@index_path}</index>\n" - h += "<count>#{@count}</count>\n" - unless @baseline.nil? - h += "<baseline>#{@baseline}</baseline>\n" - else - h += "<rule>#{@rule}</rule>\n" - end - h += "<queryOffset>#{@offset}</queryOffset>\n" - h += "<runID>#{@run_id}</runID>\n" - h += "<printQuery>#{@print_query}</printQuery>\n" - h += "<printDocuments>#{@print_docs}</printDocuments>\n" - - h - end- - diff --git a/doc/classes/RIR/Indri/Parameters.src/M000012.html b/doc/classes/RIR/Indri/Parameters.src/M000012.html deleted file mode 100644 index 23acfd5..0000000 --- a/doc/classes/RIR/Indri/Parameters.src/M000012.html +++ /dev/null @@ -1,21 +0,0 @@ - - - -
# File lib/rir/query.rb, line 30 - def initialize(corpus,mem="1g",count="1000",offset="1",run_id="default",print_query=false,print_docs=false) - @corpus = corpus - @memory = mem - @count = count - @offset = offset - @run_id = run_id - @print_query = print_query ? "true" : "false" - @print_docs = print_docs ? "true" : "false" - end- - diff --git a/doc/classes/RIR/Indri/Parameters.src/M000013.html b/doc/classes/RIR/Indri/Parameters.src/M000013.html deleted file mode 100644 index bc4b8a7..0000000 --- a/doc/classes/RIR/Indri/Parameters.src/M000013.html +++ /dev/null @@ -1,29 +0,0 @@ - - - -
# File lib/rir/query.rb, line 40 - def to_s - h = "<parameters>\n" - h += "<memory>#{@memory}</memory>\n" - h += "<index>#{@corpus}</index>\n" - h += "<count>#{@count}</count>\n" - unless @baseline.nil? - h += "<baseline>#{@baseline}</baseline>\n" - else - h += "<rule>#{@rule}</rule>\n" - end - h += "<queryOffset>#{@offset}</queryOffset>\n" - h += "<runID>#{@run_id}</runID>\n" - h += "<printQuery>#{@print_query}</printQuery>\n" - h += "<printDocuments>#{@print_docs}</printDocuments>\n" - - h - end- - diff --git a/doc/classes/RIR/Indri/Parameters.src/M000014.html b/doc/classes/RIR/Indri/Parameters.src/M000014.html deleted file mode 100644 index 3529737..0000000 --- a/doc/classes/RIR/Indri/Parameters.src/M000014.html +++ /dev/null @@ -1,29 +0,0 @@ - - - -
# File lib/rir/query.rb, line 41 - def to_s - h = "<parameters>\n" - h += "<memory>#{@memory}</memory>\n" - h += "<index>#{@corpus}</index>\n" - h += "<count>#{@count}</count>\n" - unless @baseline.nil? - h += "<baseline>#{@baseline}</baseline>\n" - else - h += "<rule>#{@rule}</rule>\n" - end - h += "<queryOffset>#{@offset}</queryOffset>\n" - h += "<runID>#{@run_id}</runID>\n" - h += "<printQuery>#{@print_query}</printQuery>\n" - h += "<printDocuments>#{@print_docs}</printDocuments>\n" - - h - end- - diff --git a/doc/classes/RIR/Indri/Parameters.src/M000016.html b/doc/classes/RIR/Indri/Parameters.src/M000016.html new file mode 100644 index 0000000..a5d26e0 --- /dev/null +++ b/doc/classes/RIR/Indri/Parameters.src/M000016.html @@ -0,0 +1,21 @@ + + + +
# File lib/rir/query.rb, line 30 + def initialize(corpus,mem="1g",count="1000",offset="1",run_id="default",print_query=false,print_docs=false) + @index_path = corpus + @memory = mem + @count = count + @offset = offset + @run_id = run_id + @print_query = print_query ? "true" : "false" + @print_docs = print_docs ? "true" : "false" + end+ + diff --git a/doc/classes/RIR/Indri/Parameters.src/M000017.html b/doc/classes/RIR/Indri/Parameters.src/M000017.html new file mode 100644 index 0000000..3a235ca --- /dev/null +++ b/doc/classes/RIR/Indri/Parameters.src/M000017.html @@ -0,0 +1,29 @@ + + + +
# File lib/rir/query.rb, line 40 + def to_s + h = "<parameters>\n" + h += "<memory>#{@memory}</memory>\n" + h += "<index>#{@index_path}</index>\n" + h += "<count>#{@count}</count>\n" + unless @baseline.nil? + h += "<baseline>#{@baseline}</baseline>\n" + else + h += "<rule>#{@rule}</rule>\n" + end + h += "<queryOffset>#{@offset}</queryOffset>\n" + h += "<runID>#{@run_id}</runID>\n" + h += "<printQuery>#{@print_query}</printQuery>\n" + h += "<printDocuments>#{@print_docs}</printDocuments>\n" + + h + end+ + diff --git a/doc/classes/RIR/TreeTagger/Chunk.html b/doc/classes/RIR/TreeTagger/Chunk.html index 95f4e8c..20dca98 100644 --- a/doc/classes/RIR/TreeTagger/Chunk.html +++ b/doc/classes/RIR/TreeTagger/Chunk.html @@ -99,7 +99,7 @@ href="TaggerChunker.html">TaggerChunker file.
# File lib/rir/ttagger.rb, line 86 - def initialize str,tag - @words = str.split - @tag = tag[1..-2] - end- - diff --git a/doc/classes/RIR/TreeTagger/Chunk.src/M000015.html b/doc/classes/RIR/TreeTagger/Chunk.src/M000015.html new file mode 100644 index 0000000..239dc5a --- /dev/null +++ b/doc/classes/RIR/TreeTagger/Chunk.src/M000015.html @@ -0,0 +1,16 @@ + + + +
# File lib/rir/ttagger.rb, line 86 + def initialize str,tag + @words = str.split + @tag = tag[1..-2] + end+ + diff --git a/doc/classes/RIR/TreeTagger/TaggerChunker.html b/doc/classes/RIR/TreeTagger/TaggerChunker.html index 57ae1ae..dc13c75 100644 --- a/doc/classes/RIR/TreeTagger/TaggerChunker.html +++ b/doc/classes/RIR/TreeTagger/TaggerChunker.html @@ -98,9 +98,9 @@ This class handles generic parsing of tagger-chunker outputs.
# File lib/rir/ttagger.rb, line 33 - def self.parse chunk_lines - open = false - tag = nil - - chunks = [] - words = [] - - chunk_lines.each do |l| - l.chomp! - if l =~ /^<\w+>$/ - open = true - tag = l - elsif l =~ /^<\/\w+>$/ - if !words.empty? && open && l == tag.sub(/</, '</') - open = false - chunks.push Chunk.new(words.join(" "), tag) - words.clear - else - next - end - else - words.push(l.split.first) - end - end - - chunks - end- - diff --git a/doc/classes/RIR/TreeTagger/TaggerChunker.src/M000002.html b/doc/classes/RIR/TreeTagger/TaggerChunker.src/M000002.html deleted file mode 100644 index c33487c..0000000 --- a/doc/classes/RIR/TreeTagger/TaggerChunker.src/M000002.html +++ /dev/null @@ -1,15 +0,0 @@ - - - -
# File lib/rir/ttagger.rb, line 65 - def initialize chunk_file - @chunks = TaggerChunker.parse File.open(chunk_file).readlines - end- - diff --git a/doc/classes/RIR/TreeTagger/TaggerChunker.src/M000013.html b/doc/classes/RIR/TreeTagger/TaggerChunker.src/M000013.html new file mode 100644 index 0000000..3bdb228 --- /dev/null +++ b/doc/classes/RIR/TreeTagger/TaggerChunker.src/M000013.html @@ -0,0 +1,39 @@ + + + +
# File lib/rir/ttagger.rb, line 33 + def self.parse chunk_lines + open = false + tag = nil + + chunks = [] + words = [] + + chunk_lines.each do |l| + l.chomp! + if l =~ /^<\w+>$/ + open = true + tag = l + elsif l =~ /^<\/\w+>$/ + if !words.empty? && open && l == tag.sub(/</, '</') + open = false + chunks.push Chunk.new(words.join(" "), tag) + words.clear + else + next + end + else + words.push(l.split.first) + end + end + + chunks + end+ + diff --git a/doc/classes/RIR/TreeTagger/TaggerChunker.src/M000014.html b/doc/classes/RIR/TreeTagger/TaggerChunker.src/M000014.html new file mode 100644 index 0000000..c33487c --- /dev/null +++ b/doc/classes/RIR/TreeTagger/TaggerChunker.src/M000014.html @@ -0,0 +1,15 @@ + + + +
# File lib/rir/ttagger.rb, line 65 + def initialize chunk_file + @chunks = TaggerChunker.parse File.open(chunk_file).readlines + end+ + diff --git a/doc/classes/RIR/WebDocument.html b/doc/classes/RIR/WebDocument.html index f2e6c6a..4f034b9 100644 --- a/doc/classes/RIR/WebDocument.html +++ b/doc/classes/RIR/WebDocument.html @@ -103,9 +103,9 @@ href="Document.html">Document with a url.
# File lib/rir/document.rb, line 112 - def self.get_content(url) - require 'net/http' - Net::HTTP.get(URI.parse(url)) - end- - diff --git a/doc/classes/RIR/WebDocument.src/M000015.html b/doc/classes/RIR/WebDocument.src/M000015.html deleted file mode 100644 index dd6da25..0000000 --- a/doc/classes/RIR/WebDocument.src/M000015.html +++ /dev/null @@ -1,16 +0,0 @@ - - - -
# File lib/rir/document.rb, line 119 - def initialize(url) - @url = url - super WebDocument.get_content(url).strip_javascripts.strip_stylesheets.strip_xml_tags - end- - diff --git a/doc/classes/RIR/WebDocument.src/M000016.html b/doc/classes/RIR/WebDocument.src/M000016.html deleted file mode 100644 index d7a5169..0000000 --- a/doc/classes/RIR/WebDocument.src/M000016.html +++ /dev/null @@ -1,16 +0,0 @@ - - - -
# File lib/rir/document.rb, line 112 - def initialize(url) - @url = url - super WebDocument.get_content(url).strip_javascripts.strip_stylesheets.strip_xml_tags - end- - diff --git a/doc/classes/RIR/WebDocument.src/M000024.html b/doc/classes/RIR/WebDocument.src/M000024.html deleted file mode 100644 index 54776b5..0000000 --- a/doc/classes/RIR/WebDocument.src/M000024.html +++ /dev/null @@ -1,16 +0,0 @@ - - - -
# File lib/rir/document.rb, line 105 - def self.get_content(url) - require 'net/http' - Net::HTTP.get(URI.parse(url)) - end- - diff --git a/doc/classes/RIR/WebDocument.src/M000025.html b/doc/classes/RIR/WebDocument.src/M000025.html deleted file mode 100644 index d7a5169..0000000 --- a/doc/classes/RIR/WebDocument.src/M000025.html +++ /dev/null @@ -1,16 +0,0 @@ - - - -
# File lib/rir/document.rb, line 112 - def initialize(url) - @url = url - super WebDocument.get_content(url).strip_javascripts.strip_stylesheets.strip_xml_tags - end- - diff --git a/doc/classes/RIR/WebDocument.src/M000028.html b/doc/classes/RIR/WebDocument.src/M000028.html new file mode 100644 index 0000000..e3931e7 --- /dev/null +++ b/doc/classes/RIR/WebDocument.src/M000028.html @@ -0,0 +1,16 @@ + + + +
# File lib/rir/document.rb, line 112 + def self.get_content(url) + require 'net/http' + Net::HTTP.get(URI.parse(url)) + end+ + diff --git a/doc/classes/RIR/WebDocument.src/M000029.html b/doc/classes/RIR/WebDocument.src/M000029.html new file mode 100644 index 0000000..dd6da25 --- /dev/null +++ b/doc/classes/RIR/WebDocument.src/M000029.html @@ -0,0 +1,16 @@ + + + +
# File lib/rir/document.rb, line 119 + def initialize(url) + @url = url + super WebDocument.get_content(url).strip_javascripts.strip_stylesheets.strip_xml_tags + end+ + diff --git a/doc/classes/RIR/WikipediaPage.html b/doc/classes/RIR/WikipediaPage.html index 02b496f..645a791 100644 --- a/doc/classes/RIR/WikipediaPage.html +++ b/doc/classes/RIR/WikipediaPage.html @@ -103,11 +103,11 @@ href="WebDocument.html">WebDocument.
# File lib/rir/document.rb, line 132 - def self.search_wikipedia_titles(name) - raise ArgumentError, "Bad encoding", name unless name.isutf8 - - res = REXML::Document.new(Net::HTTP.get( URI.parse "http://en.wikipedia.org/w/api.php?action=query&list=search&srsearch=#{URI.escape name}&format=xml" ).toutf8).elements['api/query/search'] - - res.collect { |e| e.attributes['title'] } unless res.nil? - end- - diff --git a/doc/classes/RIR/WikipediaPage.src/M000017.html b/doc/classes/RIR/WikipediaPage.src/M000017.html deleted file mode 100644 index 0b6b98b..0000000 --- a/doc/classes/RIR/WikipediaPage.src/M000017.html +++ /dev/null @@ -1,19 +0,0 @@ - - - -
# File lib/rir/document.rb, line 140 - def self.get_url(name) - raise ArgumentError, "Bad encoding", name unless name.isutf8 - - atts = REXML::Document.new(Net::HTTP.get( URI.parse "http://en.wikipedia.org/w/api.php?action=query&titles=#{URI.escape name}&inprop=url&prop=info&format=xml" ).toutf8).elements['api/query/pages/page'].attributes - - atts['fullurl'] if atts['missing'].nil? - end- - diff --git a/doc/classes/RIR/WikipediaPage.src/M000018.html b/doc/classes/RIR/WikipediaPage.src/M000018.html deleted file mode 100644 index d93d8db..0000000 --- a/doc/classes/RIR/WikipediaPage.src/M000018.html +++ /dev/null @@ -1,17 +0,0 @@ - - - -
# File lib/rir/document.rb, line 148 - def self.search_homepage(name) - title = WikipediaPage.search_wikipedia_titles name - - WikipediaPage.new(WikipediaPage.get_url title[0]) unless title.nil? || title.empty? - end- - diff --git a/doc/classes/RIR/WikipediaPage.src/M000026.html b/doc/classes/RIR/WikipediaPage.src/M000026.html deleted file mode 100644 index 3000535..0000000 --- a/doc/classes/RIR/WikipediaPage.src/M000026.html +++ /dev/null @@ -1,17 +0,0 @@ - - - -
# File lib/rir/document.rb, line 125 - def self.search_wikipedia_titles(name) - res = REXML::Document.new(Net::HTTP.get(URI.parse("http://en.wikipedia.org/w/api.php?action=query&list=search&srsearch=#{URI.escape name}&format=xml")).toutf8).elements['api/query/search'] - - res.collect { |e| e.attributes['title'] } unless res.nil? - end- - diff --git a/doc/classes/RIR/WikipediaPage.src/M000027.html b/doc/classes/RIR/WikipediaPage.src/M000027.html deleted file mode 100644 index 3023cc7..0000000 --- a/doc/classes/RIR/WikipediaPage.src/M000027.html +++ /dev/null @@ -1,17 +0,0 @@ - - - -
# File lib/rir/document.rb, line 131 - def self.get_url(name) - atts = REXML::Document.new(Net::HTTP.get(URI.parse("http://en.wikipedia.org/w/api.php?action=query&titles=#{URI.escape name}&inprop=url&prop=info&format=xml")).toutf8).elements['api/query/pages/page'].attributes - - atts['fullurl'] if atts['missing'].nil? - end- - diff --git a/doc/classes/RIR/WikipediaPage.src/M000028.html b/doc/classes/RIR/WikipediaPage.src/M000028.html deleted file mode 100644 index b5289f7..0000000 --- a/doc/classes/RIR/WikipediaPage.src/M000028.html +++ /dev/null @@ -1,21 +0,0 @@ - - - -
# File lib/rir/document.rb, line 137 - def self.search_homepage(name) - title = WikipediaPage.search_wikipedia_titles name - - begin - WikipediaPage.new(WikipediaPage.get_url title[0]) unless title.nil? || title.empty? - rescue - puts title[0] - end - end- - diff --git a/doc/classes/RIR/WikipediaPage.src/M000030.html b/doc/classes/RIR/WikipediaPage.src/M000030.html new file mode 100644 index 0000000..eb3518e --- /dev/null +++ b/doc/classes/RIR/WikipediaPage.src/M000030.html @@ -0,0 +1,19 @@ + + + +
# File lib/rir/document.rb, line 132 + def self.search_wikipedia_titles(name) + raise ArgumentError, "Bad encoding", name unless name.isutf8 + + res = REXML::Document.new(Net::HTTP.get( URI.parse "http://en.wikipedia.org/w/api.php?action=query&list=search&srsearch=#{URI.escape name}&format=xml" ).toutf8).elements['api/query/search'] + + res.collect { |e| e.attributes['title'] } unless res.nil? + end+ + diff --git a/doc/classes/RIR/WikipediaPage.src/M000031.html b/doc/classes/RIR/WikipediaPage.src/M000031.html new file mode 100644 index 0000000..0b6b98b --- /dev/null +++ b/doc/classes/RIR/WikipediaPage.src/M000031.html @@ -0,0 +1,19 @@ + + + +
# File lib/rir/document.rb, line 140 + def self.get_url(name) + raise ArgumentError, "Bad encoding", name unless name.isutf8 + + atts = REXML::Document.new(Net::HTTP.get( URI.parse "http://en.wikipedia.org/w/api.php?action=query&titles=#{URI.escape name}&inprop=url&prop=info&format=xml" ).toutf8).elements['api/query/pages/page'].attributes + + atts['fullurl'] if atts['missing'].nil? + end+ + diff --git a/doc/classes/RIR/WikipediaPage.src/M000032.html b/doc/classes/RIR/WikipediaPage.src/M000032.html new file mode 100644 index 0000000..d93d8db --- /dev/null +++ b/doc/classes/RIR/WikipediaPage.src/M000032.html @@ -0,0 +1,17 @@ + + + +
# File lib/rir/document.rb, line 148 + def self.search_homepage(name) + title = WikipediaPage.search_wikipedia_titles name + + WikipediaPage.new(WikipediaPage.get_url title[0]) unless title.nil? || title.empty? + end+ + diff --git a/doc/classes/String.html b/doc/classes/String.html index 076d643..f7f1a75 100644 --- a/doc/classes/String.html +++ b/doc/classes/String.html @@ -99,27 +99,27 @@ useful function.
# File lib/rir/string.rb, line 76 - def is_stopword? - Stoplist.include?(self.downcase) - end- - diff --git a/doc/classes/String.src/M000002.html b/doc/classes/String.src/M000002.html index c21c139..603a7ac 100644 --- a/doc/classes/String.src/M000002.html +++ b/doc/classes/String.src/M000002.html @@ -2,14 +2,14 @@ "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd"> -
# File lib/rir/string.rb, line 82 - def remove_special_characters - self.split.collect { |w| w.gsub(/\W/,' ').split.collect { |w| w.gsub(/\W/,' ').strip.sub(/\A.\z/, '')}.join(' ').strip.sub(/\A.\z/, '')}.join(' ') +# File lib/rir/string.rb, line 76 + def is_stopword? + Stoplist.include?(self.downcase) enddiff --git a/doc/classes/String.src/M000003.html b/doc/classes/String.src/M000003.html index 01c1839..c21c139 100644 --- a/doc/classes/String.src/M000003.html +++ b/doc/classes/String.src/M000003.html @@ -2,14 +2,14 @@ "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd"> -strip_xml_tags! (String) +remove_special_characters (String) -# File lib/rir/string.rb, line 91 - def strip_xml_tags! - replace strip_with_pattern /<\/?[^>]*>/ +# File lib/rir/string.rb, line 82 + def remove_special_characters + self.split.collect { |w| w.gsub(/\W/,' ').split.collect { |w| w.gsub(/\W/,' ').strip.sub(/\A.\z/, '')}.join(' ').strip.sub(/\A.\z/, '')}.join(' ') enddiff --git a/doc/classes/String.src/M000004.html b/doc/classes/String.src/M000004.html index 2d020b7..01c1839 100644 --- a/doc/classes/String.src/M000004.html +++ b/doc/classes/String.src/M000004.html @@ -2,14 +2,14 @@ "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd"> -strip_xml_tags (String) +strip_xml_tags! (String) -# File lib/rir/string.rb, line 100 - def strip_xml_tags - dup.strip_xml_tags! +# File lib/rir/string.rb, line 91 + def strip_xml_tags! + replace strip_with_pattern /<\/?[^>]*>/ enddiff --git a/doc/classes/String.src/M000005.html b/doc/classes/String.src/M000005.html index 1f77395..2d020b7 100644 --- a/doc/classes/String.src/M000005.html +++ b/doc/classes/String.src/M000005.html @@ -2,14 +2,14 @@ "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd"> -strip_javascripts! (String) +strip_xml_tags (String) -# File lib/rir/string.rb, line 114 - def strip_javascripts! - replace strip_with_pattern /<script type="text\/javascript">(.+?)<\/script>/m +# File lib/rir/string.rb, line 100 + def strip_xml_tags + dup.strip_xml_tags! enddiff --git a/doc/classes/String.src/M000006.html b/doc/classes/String.src/M000006.html index 8a73177..1f77395 100644 --- a/doc/classes/String.src/M000006.html +++ b/doc/classes/String.src/M000006.html @@ -2,14 +2,14 @@ "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd"> -strip_javascripts (String) +strip_javascripts! (String) -# File lib/rir/string.rb, line 127 - def strip_javascripts - dup.strip_javascripts! +# File lib/rir/string.rb, line 114 + def strip_javascripts! + replace strip_with_pattern /<script type="text\/javascript">(.+?)<\/script>/m enddiff --git a/doc/classes/String.src/M000007.html b/doc/classes/String.src/M000007.html index 49c5a94..8a73177 100644 --- a/doc/classes/String.src/M000007.html +++ b/doc/classes/String.src/M000007.html @@ -2,15 +2,14 @@ "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd"> -strip_stylesheets! (String) +strip_javascripts (String) -# File lib/rir/string.rb, line 131 - def strip_stylesheets! - # TODO: rewamp. dunno what is it. - replace strip_with_pattern /<style type="text\/css">(.+?)<\/style>/m +# File lib/rir/string.rb, line 127 + def strip_javascripts + dup.strip_javascripts! enddiff --git a/doc/classes/String.src/M000008.html b/doc/classes/String.src/M000008.html index a10b5bd..49c5a94 100644 --- a/doc/classes/String.src/M000008.html +++ b/doc/classes/String.src/M000008.html @@ -2,14 +2,15 @@ "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd"> -strip_stylesheets (String) +strip_stylesheets! (String) -# File lib/rir/string.rb, line 136 - def strip_stylesheets - dup.strip_stylesheets! +# File lib/rir/string.rb, line 131 + def strip_stylesheets! + # TODO: rewamp. dunno what is it. + replace strip_with_pattern /<style type="text\/css">(.+?)<\/style>/m enddiff --git a/doc/classes/String.src/M000009.html b/doc/classes/String.src/M000009.html index 37f6f1f..a10b5bd 100644 --- a/doc/classes/String.src/M000009.html +++ b/doc/classes/String.src/M000009.html @@ -2,14 +2,14 @@ "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd"> -strip_punctuation! (String) +strip_stylesheets (String) -# File lib/rir/string.rb, line 145 - def strip_punctuation! - replace strip_with_pattern /[^a-zA-Z0-9\-\s]/ +# File lib/rir/string.rb, line 136 + def strip_stylesheets + dup.strip_stylesheets! enddiff --git a/doc/classes/String.src/M000010.html b/doc/classes/String.src/M000010.html index 36b9164..37f6f1f 100644 --- a/doc/classes/String.src/M000010.html +++ b/doc/classes/String.src/M000010.html @@ -2,14 +2,14 @@ "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd"> -strip_punctuation (String) +strip_punctuation! (String) -# File lib/rir/string.rb, line 153 - def strip_punctuation - dup.strip_punctuation! +# File lib/rir/string.rb, line 145 + def strip_punctuation! + replace strip_with_pattern /[^a-zA-Z0-9\-\s]/ enddiff --git a/doc/classes/String.src/M000011.html b/doc/classes/String.src/M000011.html index c920941..36b9164 100644 --- a/doc/classes/String.src/M000011.html +++ b/doc/classes/String.src/M000011.html @@ -2,14 +2,14 @@ "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd"> -extract_xmltags_values (String) +strip_punctuation (String) -# File lib/rir/string.rb, line 161 - def extract_xmltags_values(tag_name) - self.scan(/<#{tag_name}.*?>(.+?)<\/#{tag_name}>/).flatten +# File lib/rir/string.rb, line 153 + def strip_punctuation + dup.strip_punctuation! enddiff --git a/doc/classes/String.src/M000012.html b/doc/classes/String.src/M000012.html index 427128d..c920941 100644 --- a/doc/classes/String.src/M000012.html +++ b/doc/classes/String.src/M000012.html @@ -7,7 +7,7 @@ -# File lib/rir/string.rb, line 162 +# File lib/rir/string.rb, line 161 def extract_xmltags_values(tag_name) self.scan(/<#{tag_name}.*?>(.+?)<\/#{tag_name}>/).flatten enddiff --git a/doc/created.rid b/doc/created.rid index 5367b38..6e8bb1d 100644 --- a/doc/created.rid +++ b/doc/created.rid @@ -1 +1 @@ -Thu, 25 Nov 2010 17:01:52 +0100 +Thu, 25 Nov 2010 17:10:04 +0100 diff --git a/doc/files/README_markdown.html b/doc/files/README_markdown.html deleted file mode 100644 index a52aaa0..0000000 --- a/doc/files/README_markdown.html +++ /dev/null @@ -1,121 +0,0 @@ - - - -File: README.markdown [RDoc Documentation] - - - - - - - - - --- - -README.markdown
--
-- -Path: -README.markdown - - -- -Last Update: -2010-11-05 14:46:27 +0100 -- -- - - -- -- - --- --# Ruby Information Retrieval (rIR) -
--Copyright (C) 2010-2011 Romain Deveaud
-- -License -
-=
--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 <www.gnu.org/licenses/>. -
- -- - - - - - - - - -- -- -- - - diff --git a/doc/files/lib/rir/corpus_rb.html b/doc/files/lib/rir/corpus_rb.html index 2833220..95ef563 100644 --- a/doc/files/lib/rir/corpus_rb.html +++ b/doc/files/lib/rir/corpus_rb.html @@ -87,52 +87,6 @@ You should have received a copy of the GNU General Public License along with this program. If not, see <www.gnu.org/licenses/>. --This file is a part of an Information Retrieval oriented Ruby library -
--Copyright (C) 2010-2011 Romain Deveaud
-- -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 <www.gnu.org/licenses/>. -
--This file is a part of an Information Retrieval oriented Ruby library -
--Copyright (C) 2010-2011 Romain Deveaud
-- -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 <www.gnu.org/licenses/>. -
+This file is a part of an Information Retrieval oriented Ruby library +
+
+Copyright (C) 2010-2011 Romain Deveaud
+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 <www.gnu.org/licenses/>. +
++This file is a part of an Information Retrieval oriented Ruby library +
+
+Copyright (C) 2010-2011 Romain Deveaud
+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 <www.gnu.org/licenses/>. +
+General module for many purposes related to Information Retrieval.
diff --git a/doc/files/main_rb.html b/doc/files/main_rb.html deleted file mode 100644 index 192bac7..0000000 --- a/doc/files/main_rb.html +++ /dev/null @@ -1,100 +0,0 @@ - - - -Path: | -main.rb - - | -
Last Update: | -2010-11-05 15:05:38 +0100 | -