timetwister 0.0.1 → 0.1.0

checksums.yaml

@@ -1,15 +1,15 @@
 ---
 !binary "U0hBMQ==":
   metadata.gz: !binary |-
-    YWVhN2M0NjcyMTMwNGE2ZjQ0OTRkZjM5NTE5YzE1YjM4MmQxYzVmZQ==
+    YTMxMjc2YTZiZTdkMjE4YjE2MTk5YzUyNTVkNWM1MzRmMjI4ZGVjNg==
   data.tar.gz: !binary |-
-    NDkwNjYyOGZkYzViMDE2MWE4NzM1ZTQwZmE2OGI4MDg3YTk2M2Q5Ng==
+    MWNkY2ViNzUxYWE0YzZhNWIxMTY2OWVhNjRiZjI1MDU0MWJlY2QxZQ==
 SHA512:
   metadata.gz: !binary |-
-    NmFlOWEwMDk4YjRiM2JlMDZlOWVmYjVjOGI5YjJiZTRmNTQ1NzYxMmU3YmVk
-    YTRmMDVjZGY1NWVlOTFjMzIxYTQ3ZjdmYWQ5NzlkNWExZWI5Mjc2MjJjMDMx
-    M2M4YjY4ODhiYjUyMWM0ZDA4NGVhMmIwZmFhMGJjOTVhMTc1OTM=
+    ZTgxNjhmM2ZmZTQ4NWJhOTQ1NjlhNjUzYmU4MGE3MTQ5MDc2NjhlZjQ3ZDg2
+    MmVhMGQ1OWVhMGEyMGIzMzVhMWY0MWE2ZThjZmE1ZjMwNjZhYzZiMzEyYmNk
+    ZTEzM2FlZGZjYzRiYzcwNzU4Y2MzNmUwMjVhZDM3OTQyOWUzODY=
   data.tar.gz: !binary |-
-    YmRkOTYzNTc2YjdkZTkwNzFjZTFkNWQ4ZDU4MTFlNWYyMzg5NTMyZmZmNTNh
-    MjY1ZjMwZDI0Y2RlYTIwZTYxZTU5ZTJmZmU0ZDRlNDk2YmU3MzA1Yjg2OTE3
-    OTk4MmU0NTU4Mjc5NDc4YjBkNTgwMGRlNmFiOWIyYjQ5NDNjMzI=
+    OGQxODUwNWM4NGE0M2IwNGFlOWIwZTQ5ZmNjNmNkZjQzYjJiODIxYTYyMjli
+    OTYwNWI5ZWVjMDI2NjMwMzk4Mjk4MDEwODNiZmFhNzZkY2JkNzRkZTZkYmY4
+    YTQ3NzdjODk4NjQ5ZWU3N2EwMmY5YTc5YTIyNDFhN2U1ZDFiYjc=

data/README.md

@@ -1,6 +1,8 @@
 # Timetwister
 
-TODO: Write a gem description
+A Chronic wrapper with improved date format parsing and fewer surprises.
+
+Developed by the New York Public Library to transform freetext date metadata into machine-readable data.
 
 ## Installation
 
@@ -20,12 +22,35 @@ Or install it yourself as:
 
 ## Usage
 
-TODO: Write usage instructions here
+Takes a date (or list of dates) as a string, and returns a list of hashes with parsed date data.
+
+```ruby
+require 'timetwister'
+Timetwister.parse("Jun 1898 - [July 4 1900]")
+ => [{:original_string=>"Jun 1898 - July 4 1900", :index_dates=>[1898, 1899, 1900], :date_start=>"1898-06-01", :date_end=>"1900-07-04", :date_start_full=>"1898-06-01", :date_end_full=>"1900-07-04", :inclusive_range=>true, :certainty=>"inferred", :test_data=>"330"}]
+ ```
+
+Output explanation:
+
+- `:original_string` is the original input
+- `:index_dates` is an `Array` of each year encompassed by the provided date range
+- `:date_start` and `:date_end` are ISO8601 representations of the input date, with no assumed values
+- `:date_start_full` and `:date_end_full` are ISO8601 representations of the input date in YYYY-MM-DD format (using assumed values when needed)
+- `:inclusive_range` is whether or not the input value is a range
+- `:certainty` is the certainty of the provided date, based on use of flags and punctuation
 
 ## Contributing
 
 1. Fork it ( https://github.com/[my-github-username]/timetwister/fork )
 2. Create your feature branch (`git checkout -b my-new-feature`)
-3. Commit your changes (`git commit -am 'Add some feature'`)
-4. Push to the branch (`git push origin my-new-feature`)
-5. Create a new Pull Request
+3. Update specs to test for new features (`rspec`)
+4. Commit your changes (`git commit -am 'Add some feature'`)
+5. Push to the branch (`git push origin my-new-feature`)
+6. Create a new Pull Request
+
+## Contributors
+
+- [Alex Duryee](https://github.com/alexduryee/)
+- [Trevor Thornton](https://github.com/trevorthornton/)
+- [Matt Miller](https://github.com/thisismattmiller/)
+- [Stephen Schor](https://github.com/nodanaonlyzuul/)

data/lib/timetwister/parser.rb

@@ -2,13 +2,20 @@ require 'chronic'
 
 class Parser
 
-	def self.string_to_dates(str, hash, options)
+	def self.string_to_dates(str, options)
 		@string = str
-		@dates = hash
 		@options = options
 
+		@dates = { :original_string => str, :index_dates => [], :date_start => nil, :date_end => nil,
+			:date_start_full => nil, :date_end_full => nil, :inclusive_range => nil, :certainty => nil }
+
 		@regex_tokens = regex_tokens
 
+		# defensive checks against very malformed date strings
+		if str.include?('??')
+			return @dates
+		end
+
 		# perform this here, before the string gets purged of certainty indicators
 		@dates[:certainty] = return_certainty(@string)
 

data/lib/timetwister/version.rb

@@ -1,3 +1,3 @@
 module Timetwister
-  VERSION = "0.0.1"
+  VERSION = "0.1.0"
 end

data/lib/timetwister.rb

@@ -5,16 +5,24 @@ module Timetwister
 
   	def self.parse(str, options={})
 
-		dates = { :original_string => str, :index_dates => [], :date_start => nil, :date_end => nil,
-			:date_start_full => nil, :date_end_full => nil, :inclusive_range => nil, :certainty => nil }
+  		out = []
 
-		# defensive check - we don't want to try to parse certain malformed strings
-		# (otherwise dates get flipped and types get wacky)
-		if str.include?('??')
-			return dates
-		end
+  		str.split(';').each do |semi|
+  			semi.split(' and ').each do |conj|
 
-		return Parser.string_to_dates(str, dates, options)
+  				# check for dates of form "Month Day(-Day), Year" before splitting on commas
+  				# (removes certainty markers as to not jam the regex)
+  				if conj.gsub(/[\?\[\]]/, '').match(/[JFMASOND][A-Za-z]*\.?\s[0-9]{1,2}(\s?-[0-9]{1,2})?\,\s[0-9]{4}/)
+  					out << Parser.string_to_dates(conj, options)
+  				else
+  					conj.split(',').each do |comma|
+  						out << Parser.string_to_dates(comma, options)
+  					end
+  				end
+  			end
+  		end
+
+		return out
 
 	end
 end

data/timetwister.gemspec

@@ -8,8 +8,8 @@ Gem::Specification.new do |spec|
   spec.version       = Timetwister::VERSION
   spec.authors       = ["Alex Duryee"]
   spec.email         = ["alexanderduryee@nypl.org"]
-  spec.summary       = "Chronic wrapper to handle messy date data" 
-  spec.homepage      = ""
+  spec.summary       = "Chronic wrapper to handle common date formats" 
+  spec.homepage      = "http://github.com/alexduryee/timetwister"
   spec.license       = "MIT"
 
   spec.files         = `git ls-files -z`.split("\x0")
@@ -19,4 +19,5 @@ Gem::Specification.new do |spec|
 
   spec.add_development_dependency "bundler", "~> 1.7"
   spec.add_development_dependency "rake", "~> 10.0"
+  spec.add_runtime_dependency "chronic", "~> 0.10.2"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: timetwister
 version: !ruby/object:Gem::Version
-  version: 0.0.1
+  version: 0.1.0
 platform: ruby
 authors:
 - Alex Duryee
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2015-12-10 00:00:00.000000000 Z
+date: 2015-12-11 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -38,6 +38,20 @@ dependencies:
     - - ~>
       - !ruby/object:Gem::Version
         version: '10.0'
+- !ruby/object:Gem::Dependency
+  name: chronic
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: 0.10.2
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: 0.10.2
 description: 
 email:
 - alexanderduryee@nypl.org
@@ -54,7 +68,7 @@ files:
 - lib/timetwister/parser.rb
 - lib/timetwister/version.rb
 - timetwister.gemspec
-homepage: ''
+homepage: http://github.com/alexduryee/timetwister
 licenses:
 - MIT
 metadata: {}
@@ -77,5 +91,5 @@ rubyforge_project:
 rubygems_version: 2.4.5
 signing_key: 
 specification_version: 4
-summary: Chronic wrapper to handle messy date data
+summary: Chronic wrapper to handle common date formats
 test_files: []