bibgrep 0.1.5

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 452a22378708e35559fda8ccbcb625b2c7f45a7e
+  data.tar.gz: bd4b015a50b3ff47bf612610e1a67a32930e3f6b
+SHA512:
+  metadata.gz: 93eba2c010f83f39d090fd354edc414c80c90218f65cafd49b79643abbd5dacdcabe705a23824ef25552b8eeb67d942025efd2cbc43b45655a6c90be95817886
+  data.tar.gz: 6b40f8c2bb1a00b0a64ebae81099ca2e4930c127383ef0868cc2d7c2de0c524702d13465c2754b978569c53d040dca5134fdd6b1770191e7ccadd390d7fac0e9

data/bin/bibgrep

@@ -0,0 +1,318 @@
+#!/usr/bin/env ruby
+
+# Version
+VERSION = '0.1.5 (23-04-13)'
+
+# If no regex is given,. check the field exists
+DEFAULT_RX = "\.+"
+
+# These are not technically internal keys, but metadata which
+# should still be searchable.  The is a limitation of the library.
+PSEUDO_KEYS = %w{key type}
+
+# Field separator for non-bibtex-format output
+DEFAULT_SEPARATOR = ": "
+
+OPTIONS = {
+            :f => {:desc => "Output filename (default if multiple files used)"},
+            :F => {:desc => "Suppress filename output with multiple files."},
+            :p => {:desc => "Suppress placeholders for empty fields"},
+            
+            # Raw output
+            :r => {:desc => "Output BibTeX (Cannot be used with -o)"},
+            :o => {:desc => "Specify output fields (o[=]field[,field[,field]])"},
+            :s => {:desc => "Specify field separator (s[=]sepstring).  Default is '#{DEFAULT_SEPARATOR}'."},
+
+            # Regex options
+            :v => {:desc => "Invert match"},
+            :i => {:desc => "Case-insensitive regex"},
+            :e => {:desc => "Extended regex"},
+            :m => {:desc => "Multi-line regex"},
+
+            # BibTeX options
+            :c => {:desc => "Process comment types"},
+            :w => {:desc => "Suppress BibTeX validity warnings"},
+
+            # Misc.
+            # :q => {:desc => "Suppress file warnings"},
+            :V => {:desc => "Verbose (list conditions)"},
+            :h => {:desc => "Output help"}
+          }
+
+
+# Default options to use when none are specified
+DEFAULT_OPTIONS         = "rw".chars.map{|c| c.to_sym}
+
+# Print usage, version info
+def usage
+  $stderr.puts "BibGrep v#{VERSION}"
+  $stderr.puts ""
+  $stderr.puts "USAGE: #{File.basename($0)} [-FLAGS] [-oFIELD] [-o=FIELD[,FIELD2[,...]]] [+FIELD[=RX] [+FIELD[=RX] [...]]] [FILE [FILE [...]]"
+  $stderr.puts ""
+  $stderr.puts "Where..."
+  $stderr.puts " FIELD : A BibTeX key to match on."
+  $stderr.puts "     RX : Regex to match against the field.  Omitting"
+  $stderr.puts "          a pattern means we use the default, /#{DEFAULT_RX}/"
+  $stderr.puts "   FILE : The BibTeX file(s) to parse. If your filename"
+  $stderr.puts "          begins with a dash, prefix the argument with "
+  $stderr.puts "          two dashes thus: 'lsbib -- -.bib'"
+  
+  $stderr.puts "  FIELD : One of BibTeX's field names or one of #{PSEUDO_KEYS.map{|x| "'#{x}'"}.join(", ")}."
+  $stderr.puts "          Not case-sensitive."
+  $stderr.puts "  FLAGS : A string containing some of the options below."
+  $stderr.puts "          Default is -#{DEFAULT_OPTIONS.join('')}."
+  OPTIONS.each{|k,v|
+  $stderr.puts "          -#{k} : #{v[:desc]}"
+  }
+  $stderr.puts ""
+  $stderr.puts "NB: If no files are given, I will read from stdin."
+end
+
+# Parse input options, returning:
+#  input files and filenames
+#  a hash of conditions to apply to bibtex
+#  option flags
+def parse_args
+  # Create slots for conditions and files
+  files       = {} 
+  conditions  = {}
+  options     = DEFAULT_OPTIONS
+  output      = []
+  separator   = DEFAULT_SEPARATOR
+
+  # Parse input arguments
+  force_file = false
+  default_options = true
+  ARGV.each{|a|
+
+    # Test if it's an argument or a file
+    if %w{- +}.include?(a[0]) and not force_file then
+      
+      
+      # Check for separator
+      if a == '--' then
+        # Separator, turn force file mode on
+        force_file = true
+      elsif a[0] == '+' then
+        # condition
+        a = a[1..-1]  # Remove prefixed dash
+        value = DEFAULT_RX
+        key = a
+        if equals = a.index('=') then
+          key = a[0..(equals-1)]
+          value = a[(equals+1)..-1]
+        end
+
+        # Assign to list of things to check
+        conditions[key] = value
+      elsif a[0] == '-' then
+        if default_options
+          options = [] 
+          default_options = false
+        end
+
+        # option
+        long_arg = false
+        (1..(a.length-1)).each{|i|
+          if not long_arg then
+            # Single-char options
+            o = a[i]
+          
+            if OPTIONS.keys.include?(o.to_sym)
+
+              # Handle output specially
+              if o == 'o' then
+                options << :o
+                # Tell the loop to ignore further things from this group
+                long_arg = true
+                
+                # Ignore leading equals and cut up by space
+                fields = a[(i+1)..-1].gsub(/^=/, '').split(',')
+                if fields.length > 0 then
+                  output += fields
+                end
+
+              elsif o == 's' then
+                options << :s
+                  
+                # Tell the loop to ignore further things from this group
+                long_arg = true
+                
+                # Ignore leading equals and cut up by space
+                separator = a[(i+1)..-1].gsub(/^=/, '').to_s
+              else
+                # Flag option
+                options << o.to_sym 
+              end
+            else
+              $stderr.puts "Unrecognised option: #{o}"
+              # force help
+              options << :h
+            end
+          end
+        }
+      end
+
+
+    else
+      # file
+      if not File.readable?(a) then
+        $stderr.puts "Cannot read #{a}"
+      elsif File.directory?(a) then
+        $stderr.puts "#{a} is a directory"
+      else
+        files[a] = File.open(a)
+      end
+    end
+  }
+
+  # Check that either -r or -o=field is given
+  if options.include?(:r) and output.length > 0 then
+    $stderr.puts "Option -r cannot be used with -o."
+    options << :h
+  end
+
+  # Default to stdin
+  files['<stdin>'] = STDIN if files.length == 0
+
+  # List filename by default if file length over 1
+  options << :f if not options.include?(:n) and files.length > 1
+  options.delete(:f) if options.include?(:F)
+
+  # Construct regex according to options
+  rx_flags = 0
+  rx_flags |= Regexp::IGNORECASE  if options.include?(:i)
+  rx_flags |= Regexp::EXTENDED    if options.include?(:e)
+  rx_flags |= Regexp::MULTILINE   if options.include?(:m)
+  conditions.each{ |k, v|
+    conditions[k] = Regexp.new(v, rx_flags)
+  }
+
+  return files, conditions, options.uniq, output, separator
+end
+
+# -----------------------------------------------------------------------------
+# Entry point
+# -----------------------------------------------------------------------------
+# Check the prerequisites match
+begin
+  gem 'bibtex-ruby'
+rescue
+  $stderr.puts "Please install the `bibtex-ruby' gem."
+  exit(1)
+end
+require 'bibtex'
+
+
+
+# -----------------------------------------------------------------------------
+# Load everything from ARGV
+files, conditions, options, fields, separator = parse_args
+
+
+
+
+# -----------------------------------------------------------------------------
+# If the help flag is set simply output help then exit
+if options.include?(:h) then
+  usage
+  exit(1)
+end
+
+
+
+# -----------------------------------------------------------------------------
+# Summarise, if requested
+if options.include?(:V) then
+  puts "Input files:"
+  files.keys.each{|f|
+    puts " #{f}"
+  }
+
+  puts "\nFilters:"
+  conditions.each{|k, v|
+    puts " #{k}: #{v.inspect}"
+  }
+
+  puts "\nOutput fields:"
+  fields.each{|f|
+    puts " #{f}"
+  }
+
+  puts "\nActive Options: "
+  options.each{|o|
+    puts " #{o}: #{OPTIONS[o][:desc]}"
+  }
+  puts ""
+end
+
+
+
+
+# -----------------------------------------------------------------------------
+# Processing loop proper.
+files.each{|filename, f|
+  # Check validity, but don't let it stop us parsing.
+  $stderr.puts "BibTeX file #{filename} is invalid" if not options.include?(:w) and not BibTeX.valid?(f) 
+
+  # Open file, optimistically
+  bib = BibTeX.parse(f.read)
+  bib.each{|b|
+    if options.include?(:c) or b.type.to_s.downcase != 'comment' then
+      # Perform matching by unmatching things
+      # this does an AND in the arguments list
+      match = true
+      conditions.each{|key, rx|
+
+        # Check matching on the condition, with the key or pseudo-key (object property)
+        if not ((PSEUDO_KEYS.include?(key)) ? b.send(key.to_sym) : b[key]) =~ rx
+          # cancel the match
+          match = false 
+        else
+          # Report verbose matching info
+          puts "Entry #{b.key} in file #{filename} matches on key #{key}" if options.include?(:V) 
+        end
+      }
+
+      # Invert match if requested
+      match = (not match) if options.include?(:v)
+
+      # output
+      if match then
+
+        # define output
+        output = []
+
+        # check if we want raw output or not
+        if options.include?(:r) then
+          output << b.to_s
+        else
+          # Add the filename if people want
+          output << "#{filename}" if options.include?(:f)
+
+          # Then check each option to retain order
+          # Fields are not available for comments, so simply output the contents if -c is set:
+          if options.include?(:c) and b.type.to_s.downcase == 'comment' then
+            output << b.content
+          else
+            fields.each{|f|
+              # Load value and apply placeholder if empty
+              val = nil
+              begin
+                val   = b.send(f.to_sym)
+              rescue Exception
+              end
+              val ||= "<no #{f}>" if not options.include?(:p)
+
+              # Add to the output array
+              output << val.to_s
+            }
+          end
+        end
+
+        # and output
+        puts output.join(separator.to_s) if output.length > 0
+      end
+    end
+  }
+}

metadata

@@ -0,0 +1,58 @@
+--- !ruby/object:Gem::Specification
+name: bibgrep
+version: !ruby/object:Gem::Version
+  version: 0.1.5
+platform: ruby
+authors:
+- Stephen Wattam
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2013-04-22 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: bibtex-ruby
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '2.3'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '2.3'
+description: A tool for searching and organising bibtex
+email: stephenwattam@gmail.com
+executables:
+- bibgrep
+extensions: []
+extra_rdoc_files: []
+files:
+- bin/bibgrep
+homepage: http://stephenwattam.com/projects/bibgrep
+licenses: []
+metadata: {}
+post_install_message: Have fun.
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - '>='
+    - !ruby/object:Gem::Version
+      version: '1.9'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 2.0.0
+signing_key: 
+specification_version: 4
+summary: grep for Bibtex
+test_files: []