Class: PubMed::Article
- Inherits:
-
Object
- Object
- PubMed::Article
- Defined in:
- lib/rbbt/sources/pubmed.rb
Overview
Processes the xml with an articles as served by MedLine and extracts the abstract, title and journal information
Constant Summary collapse
- XML_KEYS =
[ [:title , "ArticleTitle"], [:journal , "Journal/Title"], [:issue , "Journal/JournalIssue/Issue"], [:volume , "Journal/JournalIssue/Volume"], [:issn , "Journal/ISSN"], [:year , "Journal/JournalIssue/PubDate/Year"], [:month , "Journal/JournalIssue/PubDate/Month"], [:pages , "Pagination/MedlinePgn"], [:author , "AuthorList/Author"], [:abstract , "Abstract/AbstractText"], ]
- PMC_PDF_URL =
"http://www.ncbi.nlm.nih.gov/pmc/articles/PMCID/pdf/"
Instance Attribute Summary collapse
-
#abstract ⇒ Object
Returns the value of attribute abstract.
-
#author ⇒ Object
Returns the value of attribute author.
-
#bibentry ⇒ Object
Returns the value of attribute bibentry.
-
#gscholar_pdf ⇒ Object
Returns the value of attribute gscholar_pdf.
-
#journal ⇒ Object
Returns the value of attribute journal.
-
#pdf_url ⇒ Object
Returns the value of attribute pdf_url.
-
#pmc_pdf ⇒ Object
Returns the value of attribute pmc_pdf.
-
#pmid ⇒ Object
Returns the value of attribute pmid.
-
#title ⇒ Object
Returns the value of attribute title.
Class Method Summary collapse
- .escape_title(title) ⇒ Object
- .make_bibentry(lastname, year, title) ⇒ Object
- .parse_xml(xml) ⇒ Object
Instance Method Summary collapse
- #bibtex ⇒ Object
- #full_text ⇒ Object
-
#initialize(xml) ⇒ Article
constructor
A new instance of Article.
-
#text ⇒ Object
Join the text from title and abstract.
Constructor Details
Instance Attribute Details
#abstract ⇒ Object
Returns the value of attribute abstract.
100 101 102 |
# File 'lib/rbbt/sources/pubmed.rb', line 100 def abstract @abstract end |
#author ⇒ Object
Returns the value of attribute author.
100 101 102 |
# File 'lib/rbbt/sources/pubmed.rb', line 100 def @author end |
#bibentry ⇒ Object
Returns the value of attribute bibentry.
100 101 102 |
# File 'lib/rbbt/sources/pubmed.rb', line 100 def bibentry @bibentry end |
#gscholar_pdf ⇒ Object
Returns the value of attribute gscholar_pdf.
100 101 102 |
# File 'lib/rbbt/sources/pubmed.rb', line 100 def gscholar_pdf @gscholar_pdf end |
#journal ⇒ Object
Returns the value of attribute journal.
100 101 102 |
# File 'lib/rbbt/sources/pubmed.rb', line 100 def journal @journal end |
#pdf_url ⇒ Object
Returns the value of attribute pdf_url.
100 101 102 |
# File 'lib/rbbt/sources/pubmed.rb', line 100 def pdf_url @pdf_url end |
#pmc_pdf ⇒ Object
Returns the value of attribute pmc_pdf.
100 101 102 |
# File 'lib/rbbt/sources/pubmed.rb', line 100 def pmc_pdf @pmc_pdf end |
#pmid ⇒ Object
Returns the value of attribute pmid.
100 101 102 |
# File 'lib/rbbt/sources/pubmed.rb', line 100 def pmid @pmid end |
#title ⇒ Object
Returns the value of attribute title.
100 101 102 |
# File 'lib/rbbt/sources/pubmed.rb', line 100 def title @title end |
Class Method Details
.escape_title(title) ⇒ Object
42 43 44 |
# File 'lib/rbbt/sources/pubmed.rb', line 42 def self.escape_title(title) title.gsub(/(\w*[A-Z][A-Z]+\w*)/, '{\1}') end |
.make_bibentry(lastname, year, title) ⇒ Object
46 47 48 49 50 51 52 53 54 |
# File 'lib/rbbt/sources/pubmed.rb', line 46 def self.make_bibentry(lastname, year, title) words = title.downcase.scan(/\w+/) if words.first.length > 3 abrev = words.first else abrev = words[0..2].collect{|w| w.chars.first} * "" end [lastname.gsub(/\s/,'_'), year || "NOYEAR", abrev] * "" end |
.parse_xml(xml) ⇒ Object
55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 |
# File 'lib/rbbt/sources/pubmed.rb', line 55 def self.parse_xml(xml) parser = LibXML::XML::Parser.string(xml) pubmed = parser.parse.find("/PubmedArticle").first medline = pubmed.find("MedlineCitation").first article = medline.find("Article").first info = {} info[:pmid] = medline.find("PMID").first.content XML_KEYS.each do |p| name, key = p node = article.find(key).first next if node.nil? info[name] = node.content end bibentry = nil info[:author] = article.find("AuthorList/Author").collect do || begin lastname = .find("LastName").first.content if .find("ForeName").first.nil? forename = nil else forename = .find("ForeName").first.content.split(/\s/).collect{|word| if word.length == 1; then word + '.'; else word; end} * " " end bibentry ||= make_bibentry lastname, info[:year], info[:title] rescue end [lastname, forename] * ", " end * " and " info[:bibentry] = bibentry.downcase if bibentry info[:pmc_pdf] = pubmed.find("PubmedData/ArticleIdList/ArticleId").select{|id| id[:IdType] == "pmc"}.first if info[:pmc_pdf] info[:pmc_pdf] = PMC_PDF_URL.sub(/PMCID/, info[:pmc_pdf].content) end info end |
Instance Method Details
#bibtex ⇒ Object
140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 |
# File 'lib/rbbt/sources/pubmed.rb', line 140 def bibtex keys = [:author] + XML_KEYS.collect{|p| p.first } - [:bibentry] bibtex = "@article{#{bibentry},\n" keys.each do |key| next if self.send(key).nil? case key when :title bibtex += " title = { #{ PubMed::Article.escape_title title } },\n" when :issue bibtex += " number = { #{ issue } },\n" else bibtex += " #{ key } = { #{ self.send(key) } },\n" end end bibtex += " fulltext = { #{ pdf_url } },\n" if pdf_url bibtex += " pmid = { #{ pmid } }\n}" bibtex end |
#full_text ⇒ Object
123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 |
# File 'lib/rbbt/sources/pubmed.rb', line 123 def full_text return nil if pdf_url.nil? text = nil TmpFile.with_file do |pdf| # Change user-agent, oh well... `wget --user-agent=firefox #{ pdf_url } -O #{ pdf } -t 3` TmpFile.with_file do |txt| `pdftotext #{ pdf } #{ txt }` text = Open.read(txt) if File.exists? txt end end Misc.fixutf8(text) end |
#text ⇒ Object
Join the text from title and abstract
169 170 171 172 173 |
# File 'lib/rbbt/sources/pubmed.rb', line 169 def text text = [title, abstract].join("\n") Misc.fixutf8(text) end |