ndr_support 5.10.1 → 5.10.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: '096f063918140b27d2136df336b1ce9cc749236002d62c0c3ac6ac383b5f2295'
-  data.tar.gz: eeb407d4d7fa47c7d803b03383da810fe7ba914569923e6f8888e580f492c208
+  metadata.gz: 5f9ac10bd29787e3ff5b382618cc9389e09c1f5c1b3684a5083ca3babaa0fe99
+  data.tar.gz: d7b0273dee82913349ecc33fbd87310749e4190912ee5349000402e89e0e3e2b
 SHA512:
-  metadata.gz: 7dfffec2a85e3692e25b464ca232d1e42e4a783b5f23a6f08a3fcc0dc566ab8687b746b4fde6c206fc6f30b9e7ca674d8097b7e4b4def9928d174a19ff7fc760
-  data.tar.gz: 995d2de405da83acc432b42f3f551057537c648f3aded0d2f2625962a36069a9a37019c5fc6031880495a649389410534e30cc501a9b88df4cfd847001405e37
+  metadata.gz: 746812be4b4685cd841e7ba69eb56fa81e8f34d5d62fc5c4db1fbfdfe88dd06052df35429dcc927d43c6c1fe5b383768eec751d8c191d84283bb15737bb06138
+  data.tar.gz: 7fa1f87906e1701528f5d83268d60a664e053dd200341722c24e488eb2af4dc83ccd6d91014ecc5c893176afc71ea64510ea7e34708265b3b472432f8d2da225

data/CHANGELOG.md

@@ -1,5 +1,18 @@
 ## [Unreleased]
-* No unreleased changes
+* no unreleased changes
+
+## 5.10.3 / 2023-02-12
+## Fixed
+* Fixed issue with constant in wrong file/concern
+* Added tests for roman5 cleaning method
+* Separated log10 tests
+
+## 5.10.2 / 2024-02-09
+## Fixed
+* Refactored the cleaning code to fix Rubcocop issues
+
+## Added
+* Added a new 'log10' cleaning method
 
 ## 5.10.1 / 2024-01-04
 ## Fixed

data/code_safety.yml

@@ -22,8 +22,8 @@ file safety:
     safe_revision: 8796a1a32273a106a6b1a134a48077cff0176659
   CHANGELOG.md:
     comments:
-    reviewed_by: brian.shand
-    safe_revision: c764a4d8c251b5076ed3d60391c8271bb5a099bc
+    reviewed_by: ollietulloch
+    safe_revision: 8cb498126d68a19f880b0cd1b83b127c8ec90a89
   CODE_OF_CONDUCT.md:
     comments:
     reviewed_by: timgentry
@@ -136,10 +136,14 @@ file safety:
     comments:
     reviewed_by: brian.shand
     safe_revision: f4f7cb0803ea34a2f1ba83495d8bcbd942786bce
+  lib/ndr_support/string/clean_methodable.rb:
+    comments:
+    reviewed_by: ollietulloch
+    safe_revision: ff21f98e6608eedb4b33f977778736b38f9fbacb
   lib/ndr_support/string/cleaning.rb:
     comments:
-    reviewed_by: brianshand
-    safe_revision: b7b033ad9773cc9037c408a7763b113d31cbf191
+    reviewed_by: ollietulloch
+    safe_revision: d99c4bf5d2cbbfe78101beff399e7da8645417b2
   lib/ndr_support/string/conversions.rb:
     comments:
     reviewed_by: brian.shand
@@ -170,8 +174,8 @@ file safety:
     safe_revision: '09b3f97fb4c1afc88d0d070c39796b1f60c39d25'
   lib/ndr_support/version.rb:
     comments:
-    reviewed_by: brian.shand
-    safe_revision: 3a4b0a4acb1d6dfbfc79b17ee11577cb22ab8923
+    reviewed_by: ollietulloch
+    safe_revision: 8cb498126d68a19f880b0cd1b83b127c8ec90a89
   lib/ndr_support/working_days.rb:
     comments:
     reviewed_by: josh.pencheon
@@ -254,8 +258,8 @@ file safety:
     safe_revision: b562d0c15ff1b1d565522a47e6bae47ea09706f0
   test/string/cleaning_test.rb:
     comments:
-    reviewed_by: brianshand
-    safe_revision: b7b033ad9773cc9037c408a7763b113d31cbf191
+    reviewed_by: ollietulloch
+    safe_revision: d99c4bf5d2cbbfe78101beff399e7da8645417b2
   test/string/conversions_test.rb:
     comments:
     reviewed_by: brian.shand

data/lib/ndr_support/string/clean_methodable.rb

@@ -0,0 +1,151 @@
+# Adds the 'clean' method to String, which can be used to clean strings in various ways
+# depending on the contents
+module CleanMethodable
+  extend ActiveSupport::Concern
+
+  ROMAN_ONE_TO_FIVE_MAPPING = { 'I' => '1', 'II' => '2', 'III' => '3', 'IIII' => '4', 'IV' => '4', 'V' => '5' }.freeze
+
+  CLEAN_METHODS = {
+    nhsnumber: :clean_nhsnumber,
+    postcode: :clean_postcode, get_postcode: :clean_postcode,
+    lpi: :clean_lpi,
+    gender: :clean_gender, sex: :clean_sex, sex_c: :clean_sex_c,
+    name: :clean_name,
+    ethniccategory: :clean_ethniccategory,
+    code: :clean_code, code_icd: :clean_code_icd, icd: :clean_icd,
+    code_opcs: :clean_code_opcs,
+    hospitalnumber: :clean_hospitalnumber,
+    xmlsafe: :clean_xmlsafe, make_xml_safe: :clean_xmlsafe,
+    roman5: :clean_roman5,
+    tnmcategory: :clean_tnmcategory,
+    strip: :strip, upcase: :upcase, itself: :itself,
+    log10: :clean_log10
+  }.freeze
+
+  def clean(what)
+    cleaning_method = CLEAN_METHODS[what]
+    return send(cleaning_method) if cleaning_method
+
+    gsub(' ?', ' ')
+  end
+
+  private
+
+  def clean_nhsnumber
+    delete('^0-9')[0..9]
+  end
+
+  def clean_postcode
+    postcodeize(:db)
+  end
+
+  def clean_lpi
+    upcase.delete('^0-9A-Z')
+  end
+
+  def clean_gender
+    return '1' if self =~ /\AM(ale)?/i
+    return '2' if self =~ /\AF(emale)?/i
+
+    self
+  end
+
+  def clean_sex
+    # SECURE: BNS 2012-10-09: But may behave oddly for multi-line input
+    return '1' if self =~ /^M|1/i
+    return '2' if self =~ /^F|2/i
+
+    '0'
+  end
+
+  def clean_sex_c
+    return 'M' if self =~ /^M|1/i
+    return 'F' if self =~ /^F|2/i
+
+    ''
+  end
+
+  def clean_name
+    substitutions = {
+      '.'      => '',
+      /,|;/    => ' ',
+      /\s{2,}/ => ' ',
+      '`'      => '\''
+    }
+    substitutions.inject(upcase) { |a, e| a.gsub(*e) }.strip
+  end
+
+  def clean_ethniccategory
+    replace_ethniccategory = {
+      '0' => '0', '1' => 'M', '2' => 'N',
+      '3' => 'H', '4' => 'J', '5' => 'K',
+      '6' => 'R', '7' => '8', '&' => 'X',
+      ' ' => 'X', '99' => 'X'
+    }
+    replace_ethniccategory[self] || upcase
+  end
+
+  def clean_code
+    split_on_separators.map do |code|
+      code.blank? ? next : code.delete('.')
+    end.compact.join(' ')
+  end
+
+  def clean_code_icd
+    warn '[DEPRECATION] clean(:code_icd) is deprecated - consider using clean(:icd) instead.'
+    # regexp = /[A-Z][0-9]{2}(\.(X|[0-9]{1,2})|[0-9]?)( *(D|A)( |,|;|$))/
+    codes = upcase.split_on_separators.delete_if { |x| x.squash.blank? }
+    cleaned_codes = []
+    codes.each do |code|
+      if %w[A D].include?(code)
+        cleaned_codes[-1] += code
+      else
+        cleaned_codes << code
+      end
+    end
+    cleaned_codes.join(' ')
+  end
+
+  def clean_icd
+    codes = upcase.squish.split_on_separators.reject(&:blank?)
+    codes.map { |code| code.gsub(/(?<=\d)(\.?X?)/, '') }.join(' ')
+  end
+
+  def clean_hospitalnumber
+    self[-1..] =~ /\d/ ? self : self[0..-2]
+  end
+
+  def clean_xmlsafe
+    strip_xml_unsafe_characters
+  end
+
+  def clean_roman5
+    # This deromanises roman numerals between 1 and 5
+    gsub(/[IV]+/i) { |match| ROMAN_ONE_TO_FIVE_MAPPING[match.upcase] }
+  end
+
+  def clean_tnmcategory
+    sub!(/\A[tnm]/i, '')
+    if self =~ /\Ax\z/i
+      upcase
+    else
+      downcase
+    end
+  end
+
+  def clean_code_opcs
+    split_on_separators.map do |code|
+      db_code = code.squash
+      next unless 4 == db_code.length || db_code =~ /CZ00[12]/
+
+      db_code
+    end.compact.join(' ')
+  end
+
+  def clean_log10
+    f_value = Float(self, exception: false)
+    return self if f_value.nil? || f_value.negative?
+
+    f_value.zero? ? '0.0' : Math.log10(f_value).to_s
+  end
+end

data/lib/ndr_support/string/cleaning.rb

@@ -1,8 +1,12 @@
 require 'active_support/core_ext/string/filters'
+require 'ndr_support/string/clean_methodable'
 
+# Extends String clean with various methods of cleaning strings
+# zand polishing them
 class String
+  include CleanMethodable
+
   INVALID_CONTROL_CHARS = /[\x00-\x08\x0b-\x0c\x0e-\x1f]/
-  ROMAN_ONE_TO_FIVE_MAPPING = { 'I' => '1', 'II' => '2', 'III' => '3', 'IIII' => '4', 'IV' => '4', 'V' => '5' }
 
   POSTCODE_REGEXP = /
     ^(
@@ -26,9 +30,8 @@ class String
   # Parameter "option" can be :user, :compact, :db
   def postcodeize(option = :user)
     nspce = gsub(/[[:space:]]/, '').upcase
-    unless nspce.blank? || POSTCODE_REGEXP =~ nspce
-      return self # Don't change old-style or malformed postcodes
-    end
+    return self unless nspce.blank? || POSTCODE_REGEXP =~ nspce # Don't change old-style or malformed postcodes
+
     case option
     when :compact
       nspce
@@ -43,106 +46,6 @@ class String
     end
   end
 
-  def clean(what)
-    case what
-    when :nhsnumber
-      delete('^0-9')[0..9]
-    when :postcode, :get_postcode
-      postcodeize(:db)
-    when :lpi
-      upcase.delete('^0-9A-Z')
-    when :gender
-      if self =~ /\AM(ale)?/i
-        '1'
-      elsif self =~ /\AF(emale)?/i
-        '2'
-      else
-        self
-      end
-    when :sex
-      # SECURE: BNS 2012-10-09: But may behave oddly for multi-line input
-      if self =~ /^M|1/i
-        '1'
-      elsif self =~ /^F|2/i
-        '2'
-      else
-        '0'
-      end
-    when :sex_c
-      if self =~ /^M|1/i
-        'M'
-      elsif self =~ /^F|2/i
-        'F'
-      else
-        ''
-      end
-    when :name
-      substitutions = {
-        '.'      => '',
-        /,|;/    => ' ',
-        /\s{2,}/ => ' ',
-        '`'      => '\''
-      }
-      substitutions.inject(upcase) { |a, e| a.gsub(*e) }.strip
-    when :ethniccategory
-      replace_ethniccategory = {
-        '0' => '0',
-        '1' => 'M',
-        '2' => 'N',
-        '3' => 'H',
-        '4' => 'J',
-        '5' => 'K',
-        '6' => 'R',
-        '7' => '8',
-        '&' => 'X',
-        ' ' => 'X',
-        '99' => 'X'
-      }
-      replace_ethniccategory[self] || upcase
-    when :code
-      split_on_separators.map do |code|
-        code.blank? ? next : code.delete('.')
-      end.compact.join(' ')
-    when :code_icd
-      warn '[DEPRECATION] clean(:code_icd) is deprecated - consider using clean(:icd) instead.'
-      # regexp = /[A-Z][0-9]{2}(\.(X|[0-9]{1,2})|[0-9]?)( *(D|A)( |,|;|$))/
-      codes = upcase.split_on_separators.delete_if { |x| x.squash.blank? }
-      cleaned_codes = []
-      codes.each do |code|
-        if code == 'D' || code == 'A'
-          cleaned_codes[-1] += code
-        else
-          cleaned_codes << code
-        end
-      end
-      cleaned_codes.join(' ')
-    when :icd
-      codes = upcase.squish.split_on_separators.reject(&:blank?)
-      codes.map { |code| code.gsub(/(?<=\d)(\.?X?)/, '') }.join(' ')
-    when :code_opcs
-      clean_code_opcs
-    when :hospitalnumber
-      self[-1..-1] =~ /\d/ ? self : self[0..-2]
-    when :xmlsafe, :make_xml_safe
-      strip_xml_unsafe_characters
-    when :roman5
-      # This deromanises roman numerals between 1 and 5
-      gsub(/[IV]+/i) { |match| ROMAN_ONE_TO_FIVE_MAPPING[match.upcase] }
-    when :tnmcategory
-      sub!(/\A[tnm]/i, '')
-      if self =~ /\Ax\z/i
-        upcase
-      else
-        downcase
-      end
-    when :strip, :upcase, :itself
-      # SECURE: 14-06-2017 TPG Fixed list of executable methods (whats)
-      send(what)
-    else
-      gsub(' ?', ' ')
-    end
-  end
-
   def strip_xml_unsafe_characters
     gsub(String::INVALID_CONTROL_CHARS, '')
   end
@@ -156,14 +59,4 @@ class String
   def split_on_separators(regexp = / |,|;/)
     split(regexp)
   end
-
-  private
-
-  def clean_code_opcs
-    split_on_separators.map do |code|
-      db_code = code.squash
-      next unless 4 == db_code.length || db_code =~ /CZ00[12]/
-      db_code
-    end.compact.join(' ')
-  end
 end

data/lib/ndr_support/version.rb

@@ -3,5 +3,5 @@
 # This defines the NdrSupport version. If you change it, rebuild and commit the gem.
 # Use "rake build" to build the gem, see rake -T for all bundler rake tasks.
 module NdrSupport
-  VERSION = '5.10.1'
+  VERSION = '5.10.3'
 end

data/test/string/cleaning_test.rb

@@ -32,6 +32,25 @@ class String
       assert_equal 'HANTS', 'HANTS'.postcodeize(:db)
     end
 
+    test 'clean_log10' do
+      assert_equal '0.0', '0'.clean(:log10)
+      assert_equal '-10.1', '-10.1'.clean(:log10)
+      assert_match(/\A0.041392685158225[0-9]*\z/, '1.1'.clean(:log10),
+                   "Different ruby versions give '0.04139268515822507' or '0.04139268515822508'")
+      assert_equal 'BILBO', 'BILBO'.clean(:log10)
+    end
+
+    test 'clean_roman5' do
+      assert_equal '12345', 'I2345'.clean(:roman5)
+      assert_equal '12345', '1II345'.clean(:roman5)
+      assert_equal '12345', '12III45'.clean(:roman5)
+      assert_equal '12345', '123IIII5'.clean(:roman5)
+      assert_equal '12345', '123IIII5'.clean(:roman5)
+      assert_equal '12345', '123IV5'.clean(:roman5)
+      assert_equal '12345', '1234V'.clean(:roman5)
+      assert_equal '12345', '1II34V'.clean(:roman5)
+    end
+
     test 'xml_unsafe?' do
       without_control = 'hello world!'
       refute without_control.xml_unsafe?
@@ -153,7 +172,8 @@ class String
     end
 
     test 'clean code_icd' do
-      # TODO
+      assert_equal 'C449 Q123A Q455', 'C449,Q123,A,Q455'.clean(:code_icd)
+      assert_equal 'C449 Q123D Q455', 'C449,Q123,D,Q455'.clean(:code_icd)
     end
 
     test 'clean icd' do

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: ndr_support
 version: !ruby/object:Gem::Version
-  version: 5.10.1
+  version: 5.10.3
 platform: ruby
 authors:
 - NCRS Development Team
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2024-01-04 00:00:00.000000000 Z
+date: 2024-02-12 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: activerecord
@@ -242,6 +242,7 @@ files:
 - lib/ndr_support/regexp_range.rb
 - lib/ndr_support/safe_file.rb
 - lib/ndr_support/safe_path.rb
+- lib/ndr_support/string/clean_methodable.rb
 - lib/ndr_support/string/cleaning.rb
 - lib/ndr_support/string/conversions.rb
 - lib/ndr_support/tasks.rb
@@ -298,7 +299,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.2.33
+rubygems_version: 3.2.3
 signing_key:
 specification_version: 4
 summary: NDR Support library