diff options
Diffstat (limited to 'lib/html_word_diff.rb')
| -rw-r--r-- | lib/html_word_diff.rb | 52 |
1 files changed, 52 insertions, 0 deletions
diff --git a/lib/html_word_diff.rb b/lib/html_word_diff.rb new file mode 100644 index 0000000..1f28cf5 --- /dev/null +++ b/lib/html_word_diff.rb | |||
| @@ -0,0 +1,52 @@ | |||
| 1 | require 'diff/lcs' | ||
| 2 | |||
| 3 | module HtmlWordDiff | ||
| 4 | TOKEN_REGEXP = /<[^>]*>|[[:space:]]+|[[:alnum:]]+|[^[:space:][:alnum:]<>]/ | ||
| 5 | |||
| 6 | def self.inline(old_html, new_html) | ||
| 7 | html = +'' | ||
| 8 | each_change(old_html, new_html) do |action, old_token, new_token| | ||
| 9 | case action | ||
| 10 | when '=' | ||
| 11 | html << new_token | ||
| 12 | when '-' | ||
| 13 | html << "<del>#{old_token}</del>" | ||
| 14 | when '+' | ||
| 15 | html << "<ins>#{new_token}</ins>" | ||
| 16 | when '!' | ||
| 17 | html << "<del>#{old_token}</del><ins>#{new_token}</ins>" | ||
| 18 | end | ||
| 19 | end | ||
| 20 | html | ||
| 21 | end | ||
| 22 | |||
| 23 | def self.side_by_side(old_html, new_html) | ||
| 24 | old_out = +'' | ||
| 25 | new_out = +'' | ||
| 26 | each_change(old_html, new_html) do |action, old_token, new_token| | ||
| 27 | case action | ||
| 28 | when '=' | ||
| 29 | old_out << old_token | ||
| 30 | new_out << new_token | ||
| 31 | when '-' | ||
| 32 | old_out << "<del>#{old_token}</del>" | ||
| 33 | when '+' | ||
| 34 | new_out << "<ins>#{new_token}</ins>" | ||
| 35 | when '!' | ||
| 36 | old_out << "<del>#{old_token}</del>" | ||
| 37 | new_out << "<ins>#{new_token}</ins>" | ||
| 38 | end | ||
| 39 | end | ||
| 40 | [old_out, new_out] | ||
| 41 | end | ||
| 42 | |||
| 43 | def self.each_change(old_html, new_html) | ||
| 44 | Diff::LCS.sdiff(tokenize(old_html), tokenize(new_html)).each do |change| | ||
| 45 | yield change.action, change.old_element, change.new_element | ||
| 46 | end | ||
| 47 | end | ||
| 48 | |||
| 49 | def self.tokenize(html) | ||
| 50 | html.to_s.scan(TOKEN_REGEXP) | ||
| 51 | end | ||
| 52 | end | ||
