bio-blastxmlparser 2.0.2 → 2.0.3

data/.travis.yml

@@ -2,8 +2,8 @@ language: ruby
 rvm:
   - 1.9.3
   - jruby-19mode # JRuby in 1.9 mode
-  - rbx-19mode
   - 2.1.0
+#   - rbx-19mode
 #  - 1.8.7
 #  - jruby-18mode # JRuby in 1.8 mode
 #  - rbx-18mode

data/Gemfile

@@ -1,7 +1,7 @@
 source "http://rubygems.org"
 # Runtime dependencies
 gem "bio-logger"
-gem "nokogiri", "~>1.6.3"
+gem "nokogiri"
 
 # Add dependencies to develop your gem here.
 # Include everything needed to run rake, tests, features, etc.

data/Gemfile.lock

@@ -66,7 +66,7 @@ DEPENDENCIES
   bio-logger
   bundler
   jeweler (~> 2.0.1)
-  nokogiri (~> 1.6.3)
+  nokogiri
   rake
   rdoc
   rspec

data/README.md

@@ -2,7 +2,7 @@
 
 # bio-blastxmlparser
 
-blastxmlparser is a very fast parallelised big-data BLAST XML file
+blastxmlparser is a very fast parallel big-data BLAST XML file
 parser, which can be used as command line utility. Use blastxmlparser
 to:
 
@@ -163,6 +163,12 @@ by query iteration id, and hit_id. E.g.
   etc. etc.
 ```
 
+Another example outputs all definitions containing a string
+
+```sh
+  /blastxmlparser -n hit.hit_def --filter 'hit.hit_def=~/G. Ratti/i' 
+```
+
 ## Modify output
 
 To have more output options blastxmlparser can use an [ERB
@@ -244,7 +250,7 @@ can be
     "version":  "<%= BLASTXML_VERSION %>"
   },
 =BODY
-  { "<%= hit.parent.query_def %>": {
+  { "<%= hit.parent.query_def.strip %>": {
     "num":      <%= hit.hit_num %>,
     "id":       "<%= hit.hit_id %>",
     "len":      <%= hit.len %>,
@@ -263,13 +269,13 @@ may generate something like
     "files":    ["test/data/nt_example_blastn.m7"],
     "version":  "2.0.2-pre1"
   },
-  { "I_1 [477 - 884] ": {
+  { "I_1 [477 - 884]": {
     "num":       41,
     "id":        "lcl|X_42251",
     "len":       153,
     "E-value":   0.0247015,
   },
-  { "I_1 [477 - 884] ": {
+  { "I_1 [477 - 884]": {
     "num":       43,
     "id":        "lcl|V_105720",
     "len":       180,
@@ -279,7 +285,16 @@ may generate something like
 ```
 
 Note that the template is not smart enough to remove the final comma
-from the last BODY element. To make it valid JSON that needs to be removed.
+from the last BODY element. To make it valid JSON that needs to be
+removed. A future version may add a parameter to the BODY element or a
+global rewrite function for this purpose. A simple
+
+```ruby
+<%= ( body.last? ? "" : "," ) %>
+```
+
+does not work here because the parallel parser does not
+know which line is the last.
 
 ## Additional options
 

data/Rakefile

@@ -19,6 +19,7 @@ Jeweler::Tasks.new do |gem|
   gem.description = %Q{Fast big data BLAST XML parser and library; this libxml2 based version is 50x faster than BioRuby and comes with a nice CLI}
   gem.email = "pjotr.public01@thebird.nl"
   gem.authors = ["Pjotr Prins"]
+  gem.required_ruby_version = '>=1.9.2'
 end
 Jeweler::RubygemsDotOrgTasks.new
 

data/VERSION

@@ -1 +1 @@
-2.0.2
+2.0.3

data/bin/blastxmlparser

@@ -10,8 +10,8 @@ rootpath = File.dirname(File.dirname(__FILE__))
 $: << File.join(rootpath,'lib')
 
 BLASTXML_VERSION = File.new(File.join(rootpath,'VERSION')).read.chomp
-
-$stderr.print "BLAST XML Parser "+BLASTXML_VERSION+" Copyright (C) 2014 Pjotr Prins <pjotr.prins@thebird.nl>\n\n"
+BLASTXML_BANNER = "BLAST XML Parser "+BLASTXML_VERSION+" Copyright (C) 2014 Pjotr Prins <pjotr.prins@thebird.nl>"
+$stderr.print BLASTXML_BANNER,"\n\n"
 
 USAGE = <<EOM
 
@@ -129,6 +129,7 @@ begin
 
   raise "No input file(s) defined" if ARGV.size == 0
 
+  output_running = false # a lock for tracking the output fork
   
   ARGV.each do | fn |
     logger.info("XML parsing #{fn}")
@@ -214,15 +215,23 @@ begin
             process.call(iter,i)
           }
           # Output is forked to a separate process too
-          fork do
+          while output_running do
+            sleep 0.01
+          end
+          output_running = true
+
+          Parallel.map(1..1, :finish => lambda { |item,i,result| output_running=false }) { |num|
             output.call out
             STDOUT.flush
             STDOUT.close
-            exit 0
-          end
+          }
+
           chunks = []
         end
       end
+      while output_running do
+        sleep 0.01
+      end
       output.call Parallel.map_with_index(chunks, :in_processes => options.threads) { | iter,i |
             process.call(iter,i)
           }

data/bio-blastxmlparser.gemspec

@@ -5,11 +5,11 @@
 
 Gem::Specification.new do |s|
   s.name = "bio-blastxmlparser"
-  s.version = "2.0.2"
+  s.version = "2.0.3"
 
   s.required_rubygems_version = Gem::Requirement.new(">= 0") if s.respond_to? :required_rubygems_version=
   s.authors = ["Pjotr Prins"]
-  s.date = "2014-11-07"
+  s.date = "2015-05-07"
   s.description = "Fast big data BLAST XML parser and library; this libxml2 based version is 50x faster than BioRuby and comes with a nice CLI"
   s.email = "pjotr.public01@thebird.nl"
   s.executables = ["blastxmlparser"]
@@ -56,15 +56,16 @@ Gem::Specification.new do |s|
   s.homepage = "http://github.com/pjotrp/blastxmlparser"
   s.licenses = ["MIT"]
   s.require_paths = ["lib"]
-  s.rubygems_version = "2.0.3"
+  s.required_ruby_version = Gem::Requirement.new(">= 1.9.2")
+  s.rubygems_version = "1.8.23"
   s.summary = "Very fast parallel BLAST XML to RDF/HTML/JSON/YAML/csv transformer"
 
   if s.respond_to? :specification_version then
-    s.specification_version = 4
+    s.specification_version = 3
 
     if Gem::Version.new(Gem::VERSION) >= Gem::Version.new('1.2.0') then
       s.add_runtime_dependency(%q<bio-logger>, [">= 0"])
-      s.add_runtime_dependency(%q<nokogiri>, ["~> 1.6.3"])
+      s.add_runtime_dependency(%q<nokogiri>, [">= 0"])
       s.add_development_dependency(%q<rake>, [">= 0"])
       s.add_development_dependency(%q<bundler>, [">= 0"])
       s.add_development_dependency(%q<jeweler>, ["~> 2.0.1"])
@@ -72,7 +73,7 @@ Gem::Specification.new do |s|
       s.add_development_dependency(%q<rdoc>, [">= 0"])
     else
       s.add_dependency(%q<bio-logger>, [">= 0"])
-      s.add_dependency(%q<nokogiri>, ["~> 1.6.3"])
+      s.add_dependency(%q<nokogiri>, [">= 0"])
       s.add_dependency(%q<rake>, [">= 0"])
       s.add_dependency(%q<bundler>, [">= 0"])
       s.add_dependency(%q<jeweler>, ["~> 2.0.1"])
@@ -81,7 +82,7 @@ Gem::Specification.new do |s|
     end
   else
     s.add_dependency(%q<bio-logger>, [">= 0"])
-    s.add_dependency(%q<nokogiri>, ["~> 1.6.3"])
+    s.add_dependency(%q<nokogiri>, [">= 0"])
     s.add_dependency(%q<rake>, [">= 0"])
     s.add_dependency(%q<bundler>, [">= 0"])
     s.add_dependency(%q<jeweler>, ["~> 2.0.1"])

data/template/blast2rdf-minimal.erb

@@ -1,10 +1,24 @@
+=HEADER
+# BLAST RDF template example
+#
+#   options:  <%= options.to_h %>
+#   files:    <%= ARGV %>
+#   date:     <%= Time.now %>
+#   version:  <%= BLASTXML_BANNER %>
+
+@prefix gene: <http://biobeat.org/rdf/gwp/gene-names#> .
+@prefix : <http://biobeat.org/rdf/megablast#> .
+
+=BODY
 <%
   blastid = Turtle::mangle_identifier(hit.parent.query_def) 
   id = blastid+'_'+hit.hit_num.to_s
+  gene_name = hit.parent.query_def.split(/ /).first
 %>
 :<%= blastid %>  :query  :<%= id %>
 :<%= id %>
-  :query_def   "<%= hit.parent.query_def %>";
+  :query_def   "<%= hit.parent.query_def.strip %>";
+  gene:gene_name   "<%= gene_name %>";
   :num         <%= hit.hit_num %>;
   :accession   "<%= hit.accession %>";
   :len         <%= hit.len %>;
@@ -12,3 +26,5 @@
   :align_len   <%= hsp.align_len %>;
   :bitscore    <%= hsp.bit_score %>;
   :evalue      <%= hsp.evalue %> .
+
+=FOOTER

metadata

@@ -1,111 +1,126 @@
 --- !ruby/object:Gem::Specification
 name: bio-blastxmlparser
 version: !ruby/object:Gem::Version
-  version: 2.0.2
+  version: 2.0.3
+  prerelease: 
 platform: ruby
 authors:
 - Pjotr Prins
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2014-11-07 00:00:00.000000000 Z
+date: 2015-05-07 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bio-logger
   requirement: !ruby/object:Gem::Requirement
+    none: false
     requirements:
-    - - ">="
+    - - ! '>='
       - !ruby/object:Gem::Version
         version: '0'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
+    none: false
     requirements:
-    - - ">="
+    - - ! '>='
       - !ruby/object:Gem::Version
         version: '0'
 - !ruby/object:Gem::Dependency
   name: nokogiri
   requirement: !ruby/object:Gem::Requirement
+    none: false
     requirements:
-    - - "~>"
+    - - ! '>='
       - !ruby/object:Gem::Version
-        version: 1.6.3
+        version: '0'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
+    none: false
     requirements:
-    - - "~>"
+    - - ! '>='
       - !ruby/object:Gem::Version
-        version: 1.6.3
+        version: '0'
 - !ruby/object:Gem::Dependency
   name: rake
   requirement: !ruby/object:Gem::Requirement
+    none: false
     requirements:
-    - - ">="
+    - - ! '>='
       - !ruby/object:Gem::Version
         version: '0'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
+    none: false
     requirements:
-    - - ">="
+    - - ! '>='
       - !ruby/object:Gem::Version
         version: '0'
 - !ruby/object:Gem::Dependency
   name: bundler
   requirement: !ruby/object:Gem::Requirement
+    none: false
     requirements:
-    - - ">="
+    - - ! '>='
       - !ruby/object:Gem::Version
         version: '0'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
+    none: false
     requirements:
-    - - ">="
+    - - ! '>='
       - !ruby/object:Gem::Version
         version: '0'
 - !ruby/object:Gem::Dependency
   name: jeweler
   requirement: !ruby/object:Gem::Requirement
+    none: false
     requirements:
-    - - "~>"
+    - - ~>
       - !ruby/object:Gem::Version
         version: 2.0.1
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
+    none: false
     requirements:
-    - - "~>"
+    - - ~>
       - !ruby/object:Gem::Version
         version: 2.0.1
 - !ruby/object:Gem::Dependency
   name: rspec
   requirement: !ruby/object:Gem::Requirement
+    none: false
     requirements:
-    - - ">="
+    - - ! '>='
       - !ruby/object:Gem::Version
         version: '0'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
+    none: false
     requirements:
-    - - ">="
+    - - ! '>='
       - !ruby/object:Gem::Version
         version: '0'
 - !ruby/object:Gem::Dependency
   name: rdoc
   requirement: !ruby/object:Gem::Requirement
+    none: false
     requirements:
-    - - ">="
+    - - ! '>='
       - !ruby/object:Gem::Version
         version: '0'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
+    none: false
     requirements:
-    - - ">="
+    - - ! '>='
       - !ruby/object:Gem::Version
         version: '0'
 description: Fast big data BLAST XML parser and library; this libxml2 based version
@@ -118,9 +133,9 @@ extra_rdoc_files:
 - LICENSE.txt
 - README.md
 files:
-- ".document"
-- ".rspec"
-- ".travis.yml"
+- .document
+- .rspec
+- .travis.yml
 - Gemfile
 - Gemfile.lock
 - LICENSE.txt
@@ -155,25 +170,26 @@ files:
 homepage: http://github.com/pjotrp/blastxmlparser
 licenses:
 - MIT
-metadata: {}
 post_install_message: 
 rdoc_options: []
 require_paths:
 - lib
 required_ruby_version: !ruby/object:Gem::Requirement
+  none: false
   requirements:
-  - - ">="
+  - - ! '>='
     - !ruby/object:Gem::Version
-      version: '0'
+      version: 1.9.2
 required_rubygems_version: !ruby/object:Gem::Requirement
+  none: false
   requirements:
-  - - ">="
+  - - ! '>='
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 2.0.3
+rubygems_version: 1.8.23
 signing_key: 
-specification_version: 4
+specification_version: 3
 summary: Very fast parallel BLAST XML to RDF/HTML/JSON/YAML/csv transformer
 test_files: []

checksums.yaml

@@ -1,7 +0,0 @@
----
-SHA1:
-  metadata.gz: 76df7cd1f6e1bc4f2b04fdf3f0fc830110f2e376
-  data.tar.gz: 68f44a797aa5357690e6c4a10a1fe241a7b8fe37
-SHA512:
-  metadata.gz: f424b8cfedf921840dbf2fee412c191f1c9951d289b80db047744a56883b171b50d4b1161e86415f0e873be4bd43935031f966d32d394efea9208e65b2529903
-  data.tar.gz: 6214606ac08afa7306503c78e969046ab2a54d9c45e9dc42c597d8c033db2095fc5a25f15f56090a0337bd1049081699a81ceefa90d2acaf17cb782340074fc6