github-mirror/discourse
2
0
Fork 0
mirror of https://github.com/discourse/discourse.git synced 2025-05-31 10:10:04 +08:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

DEV: Apply syntax_tree formatting to lib/*

Browse Source
This commit is contained in:
David Taylor
2023-01-09 12:10:19 +00:00
parent b0fda61a8e
commit 6417173082
507 changed files with 16550 additions and 12627 deletions
Download Patch File Download Diff File Expand all files Collapse all files

47
lib/text_sentinel.rb
View File

@ -2,56 +2,57 @@
# We use ActiveSupport mb_chars from here to properly support non ascii downcase
# TODO remove when ruby 2.4 lands
require 'active_support/core_ext/string/multibyte'
require "active_support/core_ext/string/multibyte"
#
# Given a string, tell us whether or not is acceptable.
#
class TextSentinel
attr_accessor :text
ENTROPY_SCALE ||= 0.7
def initialize(text, opts = nil)
@opts = opts || {}
@text = text.to_s.encode('UTF-8', invalid: :replace, undef: :replace, replace: '')
@text = text.to_s.encode("UTF-8", invalid: :replace, undef: :replace, replace: "")
end
def self.body_sentinel(text, opts = {})
entropy = SiteSetting.body_min_entropy
if opts[:private_message]
scale_entropy = SiteSetting.min_personal_message_post_length.to_f / SiteSetting.min_post_length.to_f
scale_entropy =
SiteSetting.min_personal_message_post_length.to_f / SiteSetting.min_post_length.to_f
entropy = (entropy * scale_entropy).to_i
entropy = (SiteSetting.min_personal_message_post_length.to_f * ENTROPY_SCALE).to_i if entropy > SiteSetting.min_personal_message_post_length
entropy =
(SiteSetting.min_personal_message_post_length.to_f * ENTROPY_SCALE).to_i if entropy >
SiteSetting.min_personal_message_post_length
else
entropy = (SiteSetting.min_post_length.to_f * ENTROPY_SCALE).to_i if entropy > SiteSetting.min_post_length
entropy = (SiteSetting.min_post_length.to_f * ENTROPY_SCALE).to_i if entropy >
SiteSetting.min_post_length
end
TextSentinel.new(text, min_entropy: entropy)
end
def self.title_sentinel(text)
entropy = if SiteSetting.min_topic_title_length > SiteSetting.title_min_entropy
SiteSetting.title_min_entropy
else
(SiteSetting.min_topic_title_length.to_f * ENTROPY_SCALE).to_i
end
entropy =
if SiteSetting.min_topic_title_length > SiteSetting.title_min_entropy
SiteSetting.title_min_entropy
else
(SiteSetting.min_topic_title_length.to_f * ENTROPY_SCALE).to_i
end
TextSentinel.new(text, min_entropy: entropy, max_word_length: SiteSetting.title_max_word_length)
end
# Entropy is a number of how many unique characters the string needs.
# Non-ASCII characters are weighted heavier since they contain more "information"
def entropy
chars = @text.to_s.strip.split('')
@entropy ||= chars.pack('M*' * chars.size).gsub("\n", '').split('=').uniq.size
chars = @text.to_s.strip.split("")
@entropy ||= chars.pack("M*" * chars.size).gsub("\n", "").split("=").uniq.size
end
def valid?
@text.present? &&
seems_meaningful? &&
seems_pronounceable? &&
seems_unpretentious? &&
seems_quiet?
@text.present? && seems_meaningful? && seems_pronounceable? && seems_unpretentious? &&
seems_quiet?
end
def seems_meaningful?
@ -62,7 +63,7 @@ class TextSentinel
def seems_pronounceable?
# At least some non-symbol characters
# (We don't have a comprehensive list of symbols, but this will eliminate some noise)
@text.gsub(symbols_regex, '').size > 0
@text.gsub(symbols_regex, "").size > 0
end
def seems_unpretentious?
@ -70,13 +71,14 @@ class TextSentinel
# Don't allow super long words if there is a word length maximum
@opts[:max_word_length].blank? ||
(@text.split(/\s|\/|-|\.|:/).map(&:size).max || 0) <= @opts[:max_word_length]
(@text.split(%r{\s|/|-|\.|:}).map(&:size).max || 0) <= @opts[:max_word_length]
end
def seems_quiet?
return true if skipped_locale.include?(SiteSetting.default_locale)
# We don't allow all upper case content
SiteSetting.allow_uppercase_posts || @text == @text.mb_chars.downcase.to_s || @text != @text.mb_chars.upcase.to_s
SiteSetting.allow_uppercase_posts || @text == @text.mb_chars.downcase.to_s ||
@text != @text.mb_chars.upcase.to_s
end
private
@ -86,7 +88,6 @@ class TextSentinel
end
def skipped_locale
%w(zh_CN zh_TW ko ja).freeze
%w[zh_CN zh_TW ko ja].freeze
end
end