bivy 0.0.5

data/lib/journal/medline_to_full.yaml

@@ -0,0 +1,7 @@
+---
+Anal Chem: Analytical Chemistry
+Mol Cell Proteomics: Molecular and Cellular Proteomics
+Cell Signal: Cellular Signalling
+J Proteome Res: Journal of Proteome Research
+Nat Chem Biol: Nature Chemical Biology
+Nat Biotechnol: Nature Biotechnology

data/lib/journal/medline_to_iso.yaml

@@ -0,0 +1,45 @@
+--- 
+Nature: Nature
+Biomed Mass Spectrom: Biomed. Mass Spectrom.
+Nat Biotechnol: Nat. Biotechnol.
+Anal. Chem.: Anal. Chem.
+Nat Chem Biol: Nat. Chem. Biol.
+J. Proteome Res.: J. Proteome Res.
+Rapid Commun Mass Spectrom: Rapid Commun. Mass Spectrom.
+KDD Workshop on Mining Temporal and Sequential Data: KDD Workshop MTSD
+J Chromatogr B Analyt Technol Biomed Life Sci: J. Chromatogr., B
+J. Chromatogr., A: J. Chromatogr., A
+J Chemom: J. Chemom.
+Genome Res: Genome Res.
+Biomed. Mass Spectrom.: Biomed. Mass Spectrom.
+SIAM J. Num. Anal.: SIAM J. Num. Anal.
+Proteomics: Proteomics
+J. Chemom.: J. Chemom.
+Eur. Food Res. Technol.: Eur. Food Res. Technol.
+Environ Sci Technol: Environ. Sci. Technol.
+Analytica Chimica Acta: Anal. Chim. Acta
+Nature Methods: Nature Methods
+J Chromatogr A: J. Chromatogr., A
+IEEE ASSP: IEEE ASSP
+Nucleic Acids Res: Nucleic Acids Res.
+Mol Cell Proteomics: Mol. Cell. Proteomics
+J Proteome Res: J. Proteome Res.
+J Mol Biol: J. Mol. Biol.
+J. Am. Soc. Mass Spectrom.: J. Am. Soc. Mass Spectrom.
+J. Mol. Biol.: J. Mol. Biol.
+Bioinformatics: Bioinformatics
+Anal Chem: Anal. Chem.
+Mol Cell Proteomics: Mol. Cell. Proteomics
+Cell Signal: Cell Signal.
+Curr Opin Chem Biol: Curr. Opin. Chem. Biol.
+Proc IEEE Comput Syst Bioinform Conf: Proc. IEEE Comput. Syst. Bioinform. Conf.
+Lab Chip: Lab Chip
+Clin J Oncol Nurs: Clin. J. Oncol. Nurs.
+Mass Spectrom Rev: Mass Spectrom. Rev.
+Nat Protoc: Nat. Protoc.
+Conf Proc IEEE Eng Med Biol Soc: Conf. Proc. IEEE Eng. Med. Biol. Soc.
+Curr Opin Oncol: Curr. Opin. Oncol.
+J Mass Spectrom: J. Mass Spectrom.
+Trends Pharmacol Sci: Trends Pharmacol. Sci.
+Assay Drug Dev Technol: Assay Drug Dev. Technol.
+Mol Pharmacol: Mol. Pharmacol.

data/lib/media.rb

@@ -0,0 +1,88 @@
+
+module Media
+  # note that you need to add the shortcut to module Format::MediaForwarding
+  # hash if you want to be able to access it!
+
+  # add to this class the conversion from the filename (as a symbol) to the
+  # properly capitalized classname.  If the class name is just capitalized and
+  # all lower case, not necessary.
+  Symbol_to_class_string = { }
+  #:html => 'HTML'
+
+  def self.new(tp=:jtp)
+    require "media/#{tp}"
+    #puts( $".grep(/html/) )
+    klass_st = ((x = Symbol_to_class_string[tp]) ? x : tp.to_s.capitalize)
+    klass = Media.const_get(klass_st)
+    klass.new
+  end
+
+  def header
+  end
+
+  def footer
+  end
+
+  def call_it(method, string)
+    if var = string
+      send(method, var.to_s)
+    else
+      nil
+    end
+  end
+
+  def parenthesize(string)
+    '(' + string + ')' 
+  end
+
+  def bracket(string)
+    '[' + string + ']'
+  end
+
+  def br(string)
+    call_it(:bracket, string)
+  end
+
+  def par(string)
+    call_it(:parenthesize, string)
+  end
+
+  # italicize
+  def i(string)
+    call_it(:italics, string)
+  end
+
+  # bold
+  def b(string)
+    call_it(:bold, string)
+  end
+
+  # underline
+  def u(string)
+    call_it(:underline, string)
+  end
+
+  def italics(string)
+    "<span style=\"font-style:italic;\">" + string + "</span>"
+  end
+
+  def bold(string)
+    "<span style=\"font-weight:bold;\">" + string + "</span>"
+  end
+
+  def underline(string)
+    "<span style=\"text-decoration:underline;\">" + string + "</span>"
+  end
+
+  # create the final bibliography string in whatever media you desire
+  # the example here is html
+  def format(format_object, citations)
+    cts = citations.map do |cit|
+      "  <li>" + format_object.format(cit) + "</li>"
+    end
+    "<ol>\n" + cts.join("\n") + "\n</ol>\n"
+  end
+
+end
+
+

data/lib/media/html.rb

@@ -0,0 +1,65 @@
+
+class Media::HTML
+  include Media
+  Media::Symbol_to_class_string[:html] = 'HTML'
+
+  def header
+    "<html><body>"
+  end
+
+  def footer
+    "</body></html>"
+  end
+
+  def italics(string)
+    "<span style=\"font-style:italic;\">" + string + "</span>"
+  end
+
+  def bold(string)
+    "<span style=\"font-weight:bold;\">" + string + "</span>"
+  end
+
+  def underline(string)
+    "<span style=\"text-decoration:underline;\">" + string + "</span>"
+  end
+
+  def list(citations_as_strings) 
+    cts = citations_as_strings.map do |cit|
+      "\t<li>#{cit}</li>"
+    end
+    "<ol>\n" + cts.join("\n") + "\n</ol>\n"
+  end
+
+  # expects opening and closing tags.  Operates on last one.
+  # trailing text (outside a tag) is operated on if existing
+  # <tag>text</tag> => <tag>text.</tag>
+  # <tag>text</tag>more_text => '...more_text.'
+  # if the text already has a period, then no change
+  # method periodize (TODO: should alias, really)
+  def periodize(array_or_string)
+    if array_or_string.is_a?(Array)
+      array_or_string.map do |st|
+        periodize(st)
+      end
+    else
+      st = array_or_string
+      if st[-1,1] == '>'
+        st.sub(/(.*)(<\/.*?>)/) do |v|
+          if $1[-1,1] =~ /[\.\?\!]/
+            $1 + $2
+          else
+            $1 + '.' + $2
+          end
+        end
+      else
+        if st[-1,1] =~ /[\.\?\!]/
+          st
+        else
+          st << '.'
+        end
+      end
+    end
+  end
+
+end
+

data/lib/ooffice.rb

@@ -0,0 +1,39 @@
+require 'fileutils'
+FU = FileUtils
+
+class OpenOffice
+
+  # unzips the file, gives a string of the content xml and will replace it
+  # whatever you pass back (preferably a string;)
+  # requires write access to the directory where the file is located 
+  # The next time you open the file, it will act like you've corrupted the
+  # file (the character count is probably off, etc) just let it clean it up
+  # for you!
+  # new_basename = base name of the new file (preferably <name>.odt)
+  def modify_content(filename, new_basename, &blk)
+    content_file = 'content.xml'
+    basename = File.basename(filename)
+    tmpdir = basename + ".unzip.tmp"
+    Dir.chdir(File.dirname(filename)) do
+      if File.exist?(tmpdir)
+        warn "#{tmpdir} already exists!"
+        warn "deleting contents of #{tmpdir}"
+        FU.rm_rf(tmpdir)
+      end
+      FU.mkpath(tmpdir)
+      FU.cp(basename, tmpdir)
+      Dir.chdir(tmpdir) do
+        print `unzip -q #{basename}`
+        string = IO.read(content_file)
+        replace_with = blk.call(string)
+        File.open(content_file,'w') {|fh| fh.print(replace_with) }
+        FU.rm(basename, :force => true)
+        to_include = Dir["*"]
+        print `zip -r -q #{new_basename} #{to_include.map {|v| "'" + v + "'" }.join(' ')}`
+        FU.mv new_basename, '..'
+      end
+      FU.rm_rf tmpdir
+    end
+  end
+
+end

data/lib/pubmed.rb

@@ -0,0 +1,209 @@
+require 'open-uri'
+require 'rexml/document'
+require 'iconv'
+require 'citation'
+
+# given the html page where the display is specified as xml
+# extracts out the requested pieces
+class PubMed < Citation::Article
+
+  attr_accessor :pmid
+
+  # also takes pmid=hash of values to set
+  def initialize(pmid=nil, identifier=nil)
+    @quotes = []
+    if pmid.is_a? Hash
+      ########## THIS WHOLE MESS SHOULD BE ENCAPSULATED/INHERITED! but can't get
+      #inheritance with authors= working for some reason
+      @authors = []
+      pmid.each do |k,v|
+        if k == 'authors'
+          v.each do |auth|
+          if auth.is_a? String
+            authors.push( Citation::Author.from_s(auth) )
+          else
+            authors.push( auth )
+          end
+          end
+        else
+          send("#{k}=".to_sym, v)
+        end
+      end
+      ############ <-- END MESS
+    else
+      @authors = []
+      @pmid = pmid
+      @bibtype = :article
+      if pmid
+        begin
+          url = query_builder(pmid)
+          xml_string = get_xml(url)
+          extract_attrs_from_xml(xml_string)
+        end
+      end
+      if identifier
+        @ident = identifier
+      else
+        if pmid
+          @ident = create_id
+        end
+      end
+    end
+  end
+
+
+  # returns xml from online (parses html output).  No internet connection gives nil
+  def get_xml(query)
+    handle = open(query)
+    xml = handle.read
+    handle.close
+    xml
+  end
+
+  # first author's last name + year collapsing any spaces
+  def create_id
+    (@authors[0].last.to_s + @year.to_s).sub(/\s+/,'')
+  end
+
+  def inspect
+    st = "<#{self.class}:##{self.__id__} "
+    st << ( %w(authors ident quotes abstract journal_medline title year month vol issue pages).reject{|v| (v == :authors || v == :url)}.push(:bibtype).map {|v| ":#{v}=>#{send(v).inspect}"}.join(", ") )
+    st << " @authors=[#{authors.map{|g| g.inspect }.join(", ")}]"
+    st << ">"
+    st
+  end
+
+
+  # Builds the query to ask for a citation given a pubmed id
+  # valid types are xml, medline, (...need to figure out others)
+  private
+
+  # returns pubmed query based on pubmed id with xml as the output type.  Note that the xml is embedded in the page's html.
+  #   Example: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?cmd=Retrieve&db=pubmed&dopt=xml&list_uids=14654843&query_hl=6
+  #
+
+  # http://www.ncbi.nlm.nih.gov/entrez/eutils/efetch.fcgi?db=Pubmed&id=11283582&rettype=xml
+  def query_builder(pmid)
+    type = 'xml'
+    #base_url = 'http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?' 
+    base_url = 'http://www.ncbi.nlm.nih.gov/entrez/eutils/efetch.fcgi?'
+    cgi_params = ['db=Pubmed', "rettype=#{type}", 'retmode=text', "id=#{pmid}"].join('&')
+    base_url + cgi_params
+  end
+
+  # get an xml element's text according to its path (assumes single element)
+  def get_e_text(element, path)
+    #element = @xml if element == nil
+    els = element.elements.to_a(path)
+    if els.size > 1
+      raise "More than one #{path}!"
+    elsif els.size == 0
+      return nil
+    else
+      begin
+        text = els[0].get_text.value
+        return text
+      rescue NoMethodError
+        return nil
+      end
+    end
+  end
+
+  def get_author_list(xml)
+    auths = xml.elements.to_a("//PubmedArticle/MedlineCitation/Article/AuthorList/Author")
+    authors = auths.collect do |auth|
+      last_name = get_e_text(auth, "LastName")
+      initials = get_e_text(auth, "Initials")
+      ## I think we are getting author names out in UTF-8 which is not being interpreted properly.  
+      ## Transform characters into something more standard, eh
+      begin
+        last_name = Iconv.new('iso-8859-15', 'utf-8').iconv(last_name)
+      rescue Iconv::IllegalSequence
+        last_name = "**BADCHARS**"
+      end
+      begin
+        initials = Iconv.new('iso-8859-15', 'utf-8').iconv(initials)
+      rescue Iconv::IllegalSequence
+        initials = "**BADINITS**"
+      end
+      Citation::Author.new(last_name, initials)
+    end
+  end
+
+  # if they are not set from the xml, tries to set from hashes or raises a
+  # RuntimeError
+  def set_journals_or_die(journal_medline)
+    error_messages = []
+    unless @journal_iso
+      if Journal::Medline_to_ISO.key?(journal_medline)
+        @journal_iso = Journal::Medline_to_ISO[journal_medline]
+      else
+        error_messages << "Expect key for '#{journal_medline}' in Journal::Medline_to_ISO"
+        error_messages << "(alter file journal/medline_to_iso.yaml)"
+      end
+    end
+
+    unless @journal_full
+      if Journal::Medline_to_Full.key?(journal_medline)
+        @journal_full = Journal::Medline_to_Full[journal_medline]
+      else
+        error_messages << "Expect key for '#{journal_medline}' in Journal::Medline_to_Full"
+        error_messages << "(alter file journal/medline_to_full.yaml)"
+      end
+
+    end
+    if error_messages.size > 0
+      label = "******************************************************************"
+      error_messages.unshift label
+      error_messages.unshift ''
+      error_messages << "Aborting!"
+      error_messages << label
+      error_messages << ''
+      raise(error_messages.join("\n"))
+    end
+
+  end
+
+  def extract_attrs_from_xml(xml_string)
+    xml = REXML::Document.new xml_string
+    art = "//PubmedArticle/MedlineCitation/Article/"
+    @title = get_e_text(xml, art + "ArticleTitle")
+    #puts "TITLE: "
+    #puts @title
+    @journal_medline = get_e_text(xml, "//PubmedArticle/MedlineCitation/MedlineJournalInfo/MedlineTA")
+    @journal_full = get_e_text(xml, art + 'Journal/Title')
+    @journal_iso = get_e_text(xml, art + 'Journal/ISOAbbreviation')
+    set_journals_or_die(@journal_medline)
+
+    #puts "THREE JOURNALS"
+    #puts @journal_medline 
+    #puts @journal_full 
+    #puts @journal_iso 
+    @authors = get_author_list(xml)
+    iss = art + "Journal/JournalIssue/"
+    pdate = iss + "PubDate/"
+    @vol = get_e_text(xml, iss + "Volume")
+    @issue = get_e_text(xml, iss + "Issue")
+    @year = get_e_text(xml, pdate + "Year")
+    @month = get_e_text(xml, pdate + "Month")
+    @pages = get_e_text(xml, art + "Pagination/MedlinePgn") || '[Epub]'
+    @abstract = get_e_text(xml, art + "Abstract/AbstractText") || ''
+  end
+
+  # unnecessary now..
+  def pubmed_extract_xml_from_html(string)
+    html = ""
+    if string =~ /<dd><pre>(.*)<\/pre><\/dd>/m
+      html = $1
+      html.gsub!(/<\/?font.*?>/, '')
+      html.gsub!(/<\/?b.*?>/, '')
+      html.gsub!(/\&lt;/, '<')
+      html.gsub!(/\&gt;/, '>')
+      html.gsub!(/\&quot;/, '"')
+    end 
+    html 
+  end
+
+
+end
+