From a822fc513cb3c98207a14fc203c973e13f42e306 Mon Sep 17 00:00:00 2001 From: Nick LaMuro Date: Mon, 2 Oct 2017 16:03:49 -0500 Subject: Cache regexps generated from acronym_regex The Problem ----------- The following line from `String#camelize`: string = string.sub(/^(?:#{inflections.acronym_regex}(?=\b|[A-Z_])|\w)/) { |match| match.downcase } and the following line from `String#camelize`: word.gsub!(/(?:(?<=([A-Za-z\d]))|\b)(#{inflections.acronym_regex})(?=\b|[^a-z])/) { "#{$1 && '_'.freeze }#{$2.downcase}" }#{$2.downcase}" } Both generate the same regexep in the first part of the `.sub`/`.gsub` method calls every time the function is called, creating an extra object allocation each time. The value of `acronym_regex` only changes if the user decides add an acronym to the current set of inflections and apends another string on the the regexp generated here, but beyond that it remains relatively static. This has been around since acronym support was introduced back in 2011 in PR#1648. Proposed Solution ----------------- To avoid re-generating these strings every time these methods are called, cache the values of these regular expressions in the `ActiveSupport::Inflector::Inflections` instance, making it so these regular expressions are only generated once, or when the acronym's are added to. Other notable changes is the attr_readers are nodoc'd, as they shouldn't really be public APIs for users. Also, the new method, define_acronym_regex_patterns, is the only method in charge of manipulating @acronym_regex, and initialize_dup also makes use of that new change. ** Note about fix for non-deterministic actionpack test ** With the introduction of `@acronym_underscore_regex` and `@acronym_camelize_regex`, tests that manipulated these for a short time, then reset them could caused test failures to happen. This happened because the previous way we reset the `@acronyms` and `@acronym_regex` was the set them using #instance_variable_set, which wouldn't run the #define_acronym_regex_patterns method. This has now been introduced into the actionpack tests to avoid this failure. --- .../lib/active_support/inflector/inflections.rb | 20 ++++++++++++++++---- .../lib/active_support/inflector/methods.rb | 4 ++-- 2 files changed, 18 insertions(+), 6 deletions(-) (limited to 'activesupport') diff --git a/activesupport/lib/active_support/inflector/inflections.rb b/activesupport/lib/active_support/inflector/inflections.rb index a639eddf10..6cfa8bb5aa 100644 --- a/activesupport/lib/active_support/inflector/inflections.rb +++ b/activesupport/lib/active_support/inflector/inflections.rb @@ -66,17 +66,21 @@ module ActiveSupport @__instance__[locale] ||= new end - attr_reader :plurals, :singulars, :uncountables, :humans, :acronyms, :acronym_regex + attr_reader :plurals, :singulars, :uncountables, :humans, + :acronyms, :acronym_regex + attr_reader :acronyms_camelize_regex, :acronyms_underscore_regex # :nodoc: def initialize - @plurals, @singulars, @uncountables, @humans, @acronyms, @acronym_regex = [], [], Uncountables.new, [], {}, /(?=a)b/ + @plurals, @singulars, @uncountables, @humans, @acronyms = [], [], Uncountables.new, [], {} + define_acronym_regex_patterns end # Private, for the test suite. def initialize_dup(orig) # :nodoc: - %w(plurals singulars uncountables humans acronyms acronym_regex).each do |scope| + %w(plurals singulars uncountables humans acronyms).each do |scope| instance_variable_set("@#{scope}", orig.send(scope).dup) end + define_acronym_regex_patterns end # Specifies a new acronym. An acronym must be specified as it will appear @@ -130,7 +134,7 @@ module ActiveSupport # camelize 'mcdonald' # => 'McDonald' def acronym(word) @acronyms[word.downcase] = word - @acronym_regex = /#{@acronyms.values.join("|")}/ + define_acronym_regex_patterns end # Specifies a new pluralization rule and its replacement. The rule can @@ -225,6 +229,14 @@ module ActiveSupport instance_variable_set "@#{scope}", [] end end + + private + + def define_acronym_regex_patterns + @acronym_regex = @acronyms.empty? ? /(?=a)b/ : /#{@acronyms.values.join("|")}/ + @acronyms_camelize_regex = /^(?:#{@acronym_regex}(?=\b|[A-Z_])|\w)/ + @acronyms_underscore_regex = /(?:(?<=([A-Za-z\d]))|\b)(#{@acronym_regex})(?=\b|[^a-z])/ + end end # Yields a singleton instance of Inflector::Inflections so you can specify diff --git a/activesupport/lib/active_support/inflector/methods.rb b/activesupport/lib/active_support/inflector/methods.rb index 72de42b1c3..43f21c03c7 100644 --- a/activesupport/lib/active_support/inflector/methods.rb +++ b/activesupport/lib/active_support/inflector/methods.rb @@ -71,7 +71,7 @@ module ActiveSupport if uppercase_first_letter string = string.sub(/^[a-z\d]*/) { |match| inflections.acronyms[match] || match.capitalize } else - string = string.sub(/^(?:#{inflections.acronym_regex}(?=\b|[A-Z_])|\w)/) { |match| match.downcase } + string = string.sub(inflections.acronyms_camelize_regex) { |match| match.downcase } end string.gsub!(/(?:_|(\/))([a-z\d]*)/i) { "#{$1}#{inflections.acronyms[$2] || $2.capitalize}" } string.gsub!("/".freeze, "::".freeze) @@ -92,7 +92,7 @@ module ActiveSupport def underscore(camel_cased_word) return camel_cased_word unless /[A-Z-]|::/.match?(camel_cased_word) word = camel_cased_word.to_s.gsub("::".freeze, "/".freeze) - word.gsub!(/(?:(?<=([A-Za-z\d]))|\b)(#{inflections.acronym_regex})(?=\b|[^a-z])/) { "#{$1 && '_'.freeze }#{$2.downcase}" } + word.gsub!(inflections.acronyms_underscore_regex) { "#{$1 && '_'.freeze }#{$2.downcase}" } word.gsub!(/([A-Z\d]+)([A-Z][a-z])/, '\1_\2'.freeze) word.gsub!(/([a-z\d])([A-Z])/, '\1_\2'.freeze) word.tr!("-".freeze, "_".freeze) -- cgit v1.2.3