nomener 0.2.7 → 0.2.8

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: cd56c9231c23b185899cb3f0c85f7bfd050fbd0c
-  data.tar.gz: b37745c76f6263bd7fb771aab566286f44937693
+  metadata.gz: 68e937013b06402708e9f33b7105bfa96838b310
+  data.tar.gz: 52555ad53e9a6dceac49750a28f4eecba8463e51
 SHA512:
-  metadata.gz: c314a3ad037c4a9fdb120ef77fbb9c40c7998574f99c74f8062120dbefa940e7995c4def79637793b21f6d0f41d3efa747c80813fbc4403c09c06197f1e3998d
-  data.tar.gz: dcf8213aeb321016c3e01c798b379c620b178e0456780d1a6a65cd9ce43c55f2a1ed101b032888303cdded55d558b164da14b036ca4089f073dcd0a483bd34c7
+  metadata.gz: 92fe2644e1408afdfb36cfbd24bc9d9d2d5d2cf2d9b405bd875cf3e8990c7253a449106c4338e6fcf6670f0780b64a4b5ca9011426bc75cabf2faf36a9b59f43
+  data.tar.gz: dde1cdf91eac5b6ed6e0dbd9a15c077f8c3457848eead726df0a8a5838a83f1b4ac81c06f92edaedd5a3d5b7112e4734c76152489e7da9e59fb223c3b940954d

data/README.md

@@ -2,11 +2,14 @@
 [![Gem Version](https://badge.fury.io/rb/nomener.svg)](http://badge.fury.io/rb/nomener)
 [![Build Status](https://travis-ci.org/dan-ding/nomener.svg?branch=master)](https://travis-ci.org/dan-ding/nomener)
 [![Code Climate](https://codeclimate.com/github/dan-ding/nomener/badges/gpa.svg)](https://codeclimate.com/github/dan-ding/nomener)
+[![MIT license](http://img.shields.io/badge/license-MIT-brightgreen.svg)](https://github.com/dan-ding/nomener/blob/master/LICENSE.txt)
 
 Nomener assists with parsing peoples names that they give themselves (or other people). Nomener ~~is~~ was a fork of [People](https://github.com/dan-ding/people) as it uses some code contributed there. It's currently geared towards western style name formatting, however other cultural name formatting is (or would like to be supported). Currently it attempts to parse names through pattern matching without using large(r) dictionary/library/data files (except for name decorations and suffixes, see usage). It may not be possible to do without such in all languages.
 
 If you didn't know, parsing names can be much more difficult than it seems it should be.
 
+Two of the main goals are to support (a) UX in a similar manner as described by [not splitting form fields](http://www.w3.org/International/questions/qa-personal-names#singlefield) and (b) an easy manner to handle parsing of strings which contain a name.
+
 ## Requirements
 
 Requires Ruby 1.9.3 or higher (or equivalent).
@@ -36,16 +39,39 @@ name = Nomener.parse "Joe Smith" # <Nomener::Name first="Joe" last="Smith">
 Create a new instance:
 ```ruby
 name = Nomener::Name.new "Duke Joe (Henry) Smith Jr."
- # name is <Nomener::Name title="Duke" first="Joe" nick="Henry" last="Smith" suffix="Jr">
+#<Nomener::Name title="Duke" first="Joe" nick="Henry" last="Smith" suffix="Jr">
+```
+returns the same as:
+```ruby
+name = Nomener.parse "Duke Joe (Henry) Smith Jr."
 
-name.first                           # Joe
-name.name                            # Joe Smith
-"Hi #{name}!"                        # Hi Joe Smith!
-name.last                            # Smith
+name.first                           # "Joe"
+name.name                            # "Joe Smith"
+"Hi #{name}!"                        # "Hi Joe Smith!""
+name.last                            # "Smith"
 name.title                           # "Duke"
 name.suffix                          # "Jr"
 name.nick                            # "Henry"
 ```
+## Formatting
+
+The .name method accepts a string to format the name however you may like.
+It defaults to "%f %l", which is the first and last name.
+
+Other options are:
+-  %f # first name
+-  %l # last/surname/family name
+-  %m # middle name
+-  %n # nick name
+-  %m # middle name
+-  %s # suffix
+-  %t # title/prefix
+
+```ruby
+name = Nomener::Name.new "Duke Joe (Henry) Smith Jr."
+name.name "%l, %f"               # "Smith, Joe"
+name.name "%t %l"                # "Duke Smith"
+```
 
 ## TODO
 * optionally use web service api data to assist (and create the web service!)
@@ -54,6 +80,8 @@ name.nick                            # "Henry"
 * specifying formats to parse by
 * many other things
 * better non-english support
+* translations
+* NLP?
 
 ## References
 * [http://en.wikipedia.org/wiki/Personal_name](http://en.wikipedia.org/wiki/Personal_name)

data/lib/nomener/parser.rb

@@ -69,6 +69,7 @@ module Nomener
 
       # grab any identified nickname before working on the rest
       newname[:nick] = parse_nick! name
+      name.sub! NICKNAME_LEFTOVER, ""
       cleanup! name
 
       # grab any suffix' we can find
@@ -123,12 +124,7 @@ module Nomener
     #
     # Returns string of the title found or and empty string
     def self.parse_title!(nm)
-      titles = []
-      nm.gsub! TITLES do |title|
-        titles << title.strip
-        ""
-      end
-      dustoff titles.join(" ")
+      dustoff gut!(nm, TITLES)
     end
 
     # Internal: pull off what suffixes we can
@@ -138,12 +134,7 @@ module Nomener
     #
     # Returns string of the suffixes found or and empty string
     def self.parse_suffix!(nm)
-      suffixes = []
-      nm.gsub! SUFFIXES do |suffix|
-        suffixes << suffix.strip
-        ""
-      end
-      dustoff suffixes.join(" ")
+      dustoff gut!(nm, SUFFIXES)
     end
 
     # Internal: parse nickname out of string. presuming it's in quotes
@@ -153,13 +144,7 @@ module Nomener
     #
     # Returns string of the nickname found or and empty string
     def self.parse_nick!(nm)
-      nick = ""
-      nm.sub! NICKNAME do |z|
-        nick = $1.strip
-        ""
-      end
-      nm.sub! NICKNAME_LEFTOVER, ""
-      dustoff nick
+      dustoff gut!(nm, NICKNAME)
     end
 
     # Internal: parse last name from string
@@ -176,12 +161,17 @@ module Nomener
       format = :lcf if (format == :auto && nm.index(","))
 
       # these constants should have the named match :fam
-      n = nm.match( FIRSTLAST_MATCHER ) if format == :fl
-      n = nm.match( LASTFIRST_MATCHER ) if format == :lf
-      n = nm.match( LASTCOMFIRST_MATCHER ) if format == :lcf
+      nomen = case format
+        when :fl
+          nm.match( FIRSTLAST_MATCHER )
+        when :lf
+          nm.match( LASTFIRST_MATCHER )
+        when :lcf
+          nm.match( LASTCOMFIRST_MATCHER )
+      end
 
-      unless n.nil?
-        last = n[:fam].strip if n[:fam]
+      unless nomen.nil? || nomen[:fam].nil?
+        last = nomen[:fam].strip
         nm.sub!(last, "")
         nm.sub!(",", "")
       end
@@ -233,5 +223,20 @@ module Nomener
       str = str.squeeze " "
       str = str.strip
     end
+
+    # Internal: clean out a given string with a given pattern
+    #   Modfies the given string
+    # str - the string to gut
+    # pattern - the regext to cut with
+    #
+    # Returns the gutted pattern
+    def self.gut!(str = "", pattern = / /)
+      found = []
+      str.gsub! pattern do |pat|
+        found << pat.strip
+        ""
+      end
+      found.join " "
+    end
   end
-end
+end

data/lib/nomener/version.rb

@@ -1,4 +1,4 @@
 #-- encoding: UTF-8
 module Nomener
-  VERSION = "0.2.7"
+  VERSION = "0.2.8"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: nomener
 version: !ruby/object:Gem::Version
-  version: 0.2.7
+  version: 0.2.8
 platform: ruby
 authors:
 - Dante Piombino
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2015-04-12 00:00:00.000000000 Z
+date: 2015-04-14 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler