parse_date 0.0.1 → 0.1.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 501a6ce6db3b6f30cf1447079027cc3e1f2d80fc2410636190483aadbddb7d7b
-  data.tar.gz: 649cf13aa5b94b32d54b7bdba6b6199021ec885ec49cb0899e9b8ef5a5319f94
+  metadata.gz: 67507d7ddc6be0cff379b210ca3985316153e96823ee573f6292298746fd25f7
+  data.tar.gz: 87ffbb778c68a34a472f99429252172bb676738d48a6776e3a5195b871397afd
 SHA512:
-  metadata.gz: 4287a85f179120c0de4be292e8a2eb73c7966884c4ce03031e87772c0a66a5f8254e3c2055a0e187b4cb764b991e23f39380e362848bc5d87219d66c634fde0a
-  data.tar.gz: 4ba900b4300aa88900ad803a1d8acaf4c180c48260546c73d7fdfc4a78e20090a5a01308307d0c657287f33fe8546798bfa84e3a1b50341d482dcd66db046204
+  metadata.gz: a89b5cd3b4712bae4a0d82e5624b2463a10719243b19cc5d4b28d6d95db2ed097691fcc4c0a39a6e319db46cb0d6a6972b2bdda9530b6fc3d75d5e52e7ba6fcf
+  data.tar.gz: 634e22955684ec3176217d4ebfe16434bcffca287b8d64f30a53332c93e2b992cd995997956799aec53e0b7a68560de49ba23cdf6efdaf332dd4bad6ef91e18e

data/.rubocop.yml

@@ -6,16 +6,17 @@ AllCops:
 Layout/EmptyLinesAroundClassBody:
   Enabled: false
 
+Layout/EmptyLinesAroundModuleBody:
+  Enabled: false
+
 Metrics/LineLength:
   Max: 120
 
 Metrics/MethodLength:
   Max: 15
 
-Style/Documentation:
-  Exclude:
-    - 'spec/**/*'
-    - 'lib/parse_date.rb'
-
 Style/WordArray:
   Enabled: false
+
+Style/YodaCondition:
+  Enabled: false

data/.rubocop_todo.yml

@@ -1,7 +1,56 @@
 # This configuration was generated by
 # `rubocop --auto-gen-config`
-# on 2019-09-27 15:27:21 -0700 using RuboCop version 0.74.0.
+# on 2019-10-01 18:08:41 -0700 using RuboCop version 0.74.0.
 # The point is for the user to remove these configuration records
 # one by one as the offenses are removed from the code base.
 # Note that changes in the inspected code, or installation of new
 # versions of RuboCop, may require this file to be generated again.
+
+# Offense count: 3
+Metrics/AbcSize:
+  Max: 22
+
+# Offense count: 2
+# Configuration parameters: CountComments, ExcludedMethods.
+# ExcludedMethods: refine
+Metrics/BlockLength:
+  Max: 512
+
+# Offense count: 3
+Metrics/CyclomaticComplexity:
+  Max: 9
+
+# Offense count: 2
+Metrics/PerceivedComplexity:
+  Max: 9
+
+# Offense count: 2
+Style/Documentation:
+  Exclude:
+    - 'spec/**/*'
+    - 'test/**/*'
+    - 'lib/parse_date.rb'
+
+# Offense count: 1
+# Cop supports --auto-correct.
+# Configuration parameters: EnforcedOctalStyle.
+# SupportedOctalStyles: zero_with_o, zero_only
+Style/NumericLiteralPrefix:
+  Exclude:
+    - 'spec/parse_date/int_from_string_spec.rb'
+
+# Offense count: 1
+# Cop supports --auto-correct.
+# Configuration parameters: EnforcedStyle, AllowInnerSlashes.
+# SupportedStyles: slashes, percent_r, mixed
+Style/RegexpLiteral:
+  Exclude:
+    - 'lib/parse_date/int_from_string.rb'
+
+# Offense count: 1
+# Cop supports --auto-correct.
+# Configuration parameters: EnforcedStyleForMultiline.
+# SupportedStylesForMultiline: comma, consistent_comma, no_comma
+Style/TrailingCommaInArrayLiteral:
+  Exclude:
+    - 'spec/parse_date/int_from_string_spec.rb'

data/README.md

@@ -25,7 +25,35 @@ Or install it yourself as:
 
 ## Usage
 
-TODO: Write usage instructions here
+ParseDate has class methods for date string parsing.
+
+```
+require 'parse_date'
+
+ParseDate.year_int_from_date_str('12/25/00') # 2000
+ParseDate.year_int_from_date_str('5-1-21') # 1921
+ParseDate.year_int_from_date_str('18th century CE') # 1700
+ParseDate.year_int_from_date_str('1666 B.C.') # -1666
+ParseDate.year_int_from_date_str('17uu') # 1700
+ParseDate.year_int_from_date_str('-914') # -914
+ParseDate.year_int_from_date_str('[c1926]') # 1926
+ParseDate.year_int_from_date_str('ca. 1558') # 1558
+
+ParseDate.year_int_valid?(0) # true
+ParseDate.year_int_valid?(5) # true
+ParseDate.year_int_valid?(33) # true
+ParseDate.year_int_valid?(150) # true
+ParseDate.year_int_valid?(2019) # true
+ParseDate.year_int_valid?(Date.today.year + 1) # true
+ParseDate.year_int_valid?(-3) # true
+ParseDate.year_int_valid?(-35) # true
+ParseDate.year_int_valid?(-999) # true
+ParseDate.year_int_valid?(-1666) # false - four digit negative years not considered valid here
+ParseDate.year_int_valid?(165x) # false
+ParseDate.year_int_valid?(198-) # false
+ParseDate.year_int_valid?('random text') # false
+ParseDate.year_int_valid?(nil) # false
+```
 
 ## Development
 

data/lib/parse_date.rb

@@ -1,5 +1,6 @@
 # frozen_string_literal: true
 
+require 'singleton'
 require 'zeitwerk'
 
 class ParseDateInflector < Zeitwerk::Inflector
@@ -18,7 +19,19 @@ loader.inflector = ParseDateInflector.new
 loader.push_dir(File.absolute_path("#{__FILE__}/.."))
 loader.setup
 
-module ParseDate
+class ParseDate
   class Error < StandardError; end
-  # Your code goes here...
+
+  include Singleton
+  extend ParseDate::IntFromString
+
+  # class method delegation for ParseDate.year_int_from_date_str
+  def self.year_int_from_date_str(orig_date_str)
+    ParseDate::IntFromString.year_int_from_date_str(orig_date_str)
+  end
+
+  # class method delegation for ParseDate.year_int_valid?
+  def self.year_int_valid?(orig_date_str)
+    ParseDate::IntFromString.year_int_valid?(orig_date_str)
+  end
 end

data/lib/parse_date/int_from_string.rb

@@ -0,0 +1,145 @@
+# frozen_string_literal: true
+
+require 'date' # so upstream callers don't have to require it
+
+class ParseDate
+
+  # Parse (Year) Integers from Date Strings
+  module IntFromString
+
+    # get Integer year if we can parse date_str to get a year.
+    # NOTE:  if we have a x/x/yy or x-x-yy pattern (the only 2 digit year patterns
+    #   found in our actual date strings in stanford-mods records), then
+    #   we use 20 as century digits unless it is greater than current year:
+    #   1/1/17  ->  2017
+    #   1/1/27  ->  1927
+    # @return [Integer, nil] Integer year if we could parse one, nil otherwise
+    def self.year_int_from_date_str(orig_date_str)
+      return if orig_date_str == '0000-00-00' # shpc collection has these useless dates
+      # B.C. first in case there are 4 digits, e.g. 1600 B.C.
+      return ParseDate.send(:sortable_year_int_for_bc, orig_date_str) if orig_date_str.match(BC_REGEX)
+
+      result = ParseDate.send(:sortable_year_for_yyyy_or_yy, orig_date_str)
+      result ||= ParseDate.send(:sortable_year_for_decade, orig_date_str) # 19xx or 20xx
+      result ||= ParseDate.send(:sortable_year_for_century, orig_date_str)
+      result ||= ParseDate.send(:sortable_year_int_for_early_numeric, orig_date_str)
+      unless result
+        # try removing brackets between digits in case we have 169[5] or [18]91
+        no_brackets = ParseDate.send(:remove_brackets, orig_date_str)
+        return year_int_from_date_str(no_brackets) if no_brackets
+      end
+      result.to_i if result && year_int_valid?(result.to_i)
+    end
+
+    # true if the year is between -999 and (current year + 1)
+    # @return [Boolean] true if the year is between -999 and (current year + 1); false otherwise
+    def self.year_int_valid?(year)
+      return false unless year.is_a? Integer
+
+      (-1000 < year.to_i) && (year < Date.today.year + 2)
+    end
+
+    protected
+
+    # get String sortable value year if we can parse date_str to get a year.
+    # @return [String, nil] String sortable year if we could parse one, nil otherwise
+    #  note that these values must *lexically* sort to create a chronological sort.
+    def sortable_year_for_yyyy_or_yy(orig_date_str)
+      # most date strings have a four digit year
+      result = ParseDate.sortable_year_for_yyyy(orig_date_str)
+      result ||= ParseDate.sortable_year_for_yy(orig_date_str) # 19xx or 20xx
+      result
+    end
+
+    BRACKETS_BETWEEN_DIGITS_REXEXP = Regexp.new('\d[' + Regexp.escape('[]') + ']\d')
+
+    # removes brackets between digits such as 169[5] or [18]91
+    def remove_brackets(orig_date_str)
+      orig_date_str.delete('[]') if orig_date_str.match(BRACKETS_BETWEEN_DIGITS_REXEXP)
+    end
+
+    # looks for 4 consecutive digits in orig_date_str and returns first occurrence if found
+    # @return [String, nil] 4 digit year (e.g. 1865, 0950) if orig_date_str has yyyy, nil otherwise
+    def sortable_year_for_yyyy(orig_date_str)
+      matches = orig_date_str.match(/\d{4}/) if orig_date_str
+      matches&.to_s
+    end
+
+    # returns 4 digit year as String if we have a x/x/yy or x-x-yy pattern
+    #   note that these are the only 2 digit year patterns found in our actual date strings in stanford-mods records
+    #   we use 20 as century digits unless it is greater than current year:
+    #   1/1/17  ->  2017
+    #   1/1/27  ->  1927
+    # @return [String, nil] 4 digit year (e.g. 1865, 0950) if orig_date_str matches pattern, nil otherwise
+    def sortable_year_for_yy(orig_date_str)
+      return unless orig_date_str
+
+      slash_matches = orig_date_str.match(/\d{1,2}\/\d{1,2}\/\d{2}/)
+      if slash_matches
+        date_obj = Date.strptime(orig_date_str, '%m/%d/%y')
+      else
+        hyphen_matches = orig_date_str.match(/\d{1,2}-\d{1,2}-\d{2}/)
+        date_obj = Date.strptime(orig_date_str, '%m-%d-%y') if hyphen_matches
+      end
+      date_obj = Date.new(date_obj.year - 100, date_obj.month, date_obj.mday) if date_obj && date_obj > Date.today
+      date_obj.year.to_s if date_obj
+    rescue ArgumentError
+      nil # explicitly want nil if date won't parse
+    end
+
+    DECADE_4CHAR_REGEXP = Regexp.new('(^|\D)\d{3}[u\-?x]')
+
+    # get first year of decade (as String) if we have:  yyyu, yyy-, yyy? or yyyx pattern
+    #   note that these are the only decade patterns found in our actual date strings in MODS records
+    # @return [String, nil] 4 digit year (e.g. 1860, 1950) if orig_date_str matches pattern, nil otherwise
+    def sortable_year_for_decade(orig_date_str)
+      decade_matches = orig_date_str.match(DECADE_4CHAR_REGEXP) if orig_date_str
+      changed_to_zero = decade_matches.to_s.tr('u\-?x', '0') if decade_matches
+      ParseDate.sortable_year_for_yyyy(changed_to_zero) if changed_to_zero
+    end
+
+    CENTURY_WORD_REGEXP = Regexp.new('(\d{1,2}).*century')
+    CENTURY_4CHAR_REGEXP = Regexp.new('(\d{1,2})[u\-]{2}([^u\-]|$)')
+
+    # get first year of century (as String) if we have:  yyuu, yy--, yy--? or xxth century pattern
+    #   note that these are the only century patterns found in our actual date strings in MODS records
+    # @return [String, nil] yy00 if orig_date_str matches pattern, nil otherwise; also nil if B.C. in pattern
+    def sortable_year_for_century(orig_date_str)
+      return unless orig_date_str
+      return if orig_date_str =~ /B\.C\./
+
+      century_matches = orig_date_str.match(CENTURY_4CHAR_REGEXP)
+      if century_matches
+        m = Regexp.last_match(1)
+        return m + '00' if m.length == 2
+        return '0' + m + '00' if m.length == 1
+      end
+
+      century_str_matches = orig_date_str.match(CENTURY_WORD_REGEXP)
+      return unless century_str_matches
+
+      yy = (Regexp.last_match(1).to_i - 1).to_s
+      return yy + '00' if yy.length == 2
+      return '0' + yy + '00' if yy.length == 1
+    end
+
+    BC_REGEX = Regexp.new('(\d{1,4}).*' + Regexp.escape('B.C.'))
+
+    # get Integer sortable value for B.C. if we have B.C. pattern
+    # @return [Integer, nil] Integer sortable -ddd if B.C. in pattern; nil otherwise
+    def sortable_year_int_for_bc(orig_date_str)
+      bc_matches = orig_date_str.match(BC_REGEX) if orig_date_str
+      "-#{Regexp.last_match(1)}".to_i if bc_matches
+    end
+
+    EARLY_NUMERIC = Regexp.new('^\-?\d{1,3}$')
+
+    # get Integer sortable value from date String containing yyy, yy, y, -y, -yy, -yyy, -yyyy
+    # @return [Integer, nil] Integer sortable -ddd if orig_date_str matches pattern; nil otherwise
+    def sortable_year_int_for_early_numeric(orig_date_str)
+      return orig_date_str.to_i if orig_date_str.match(EARLY_NUMERIC)
+
+      orig_date_str.to_i if orig_date_str =~ /^-\d{4}$/
+    end
+  end
+end

data/lib/parse_date/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
-module ParseDate
-  VERSION = '0.0.1'
+class ParseDate
+  VERSION = '0.1.0'
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: parse_date
 version: !ruby/object:Gem::Version
-  version: 0.0.1
+  version: 0.1.0
 platform: ruby
 authors:
 - Naomi Dushay
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2019-09-27 00:00:00.000000000 Z
+date: 2019-10-07 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: zeitwerk
@@ -129,6 +129,7 @@ files:
 - bin/console
 - bin/setup
 - lib/parse_date.rb
+- lib/parse_date/int_from_string.rb
 - lib/parse_date/version.rb
 - parse_date.gemspec
 homepage: https://github.com/sul-dlss/parse_date