Class: Canon::DiffFormatter::ByLine::HtmlFormatter

Inherits:
BaseFormatter
  • Object
show all
Defined in:
lib/canon/diff_formatter/by_line/html_formatter.rb

Overview

HTML formatter with DOM-guided diffing Uses DOM parsing and element matching for intelligent HTML diffs

Instance Attribute Summary collapse

Attributes inherited from BaseFormatter

#context_lines, #diff_grouping_lines, #diff_mode, #legacy_terminal, #show_diffs, #use_color, #visualization_map

Instance Method Summary collapse

Methods inherited from BaseFormatter

#apply_bg, #apply_color, #apply_theme_style, #changed_content_styles, #compute_line_num_width, #content_style, #display_mode, for_format, #marker_style, #normalize_color_for_rainbow, #structure_color, #structure_styles, #styled_marker, #theme, #theme_color, #theme_style, #unchanged_content_style, #visualization_chars

Constructor Details

#initialize(use_color: true, context_lines: 3, diff_grouping_lines: nil, visualization_map: nil, html_version: :html4, show_diffs: :all, differences: [], diff_mode: :separate, legacy_terminal: false, equivalent: nil) ⇒ HtmlFormatter

Returns a new instance of HtmlFormatter.



15
16
17
18
19
20
21
22
23
24
25
26
27
 
# File 'lib/canon/diff_formatter/by_line/html_formatter.rb', line 15

def initialize(use_color: true, context_lines: 3,
               diff_grouping_lines: nil, visualization_map: nil,
               html_version: :html4, show_diffs: :all, differences: [],
               diff_mode: :separate, legacy_terminal: false,
               equivalent: nil)
  super(use_color: use_color, context_lines: context_lines,
        diff_grouping_lines: diff_grouping_lines,
        visualization_map: visualization_map,
        show_diffs: show_diffs, differences: differences,
        diff_mode: diff_mode, legacy_terminal: legacy_terminal,
        equivalent: equivalent)
  @html_version = html_version
end

Instance Attribute Details

#html_version ⇒ Object (readonly)

Returns the value of attribute html_version.



13
14
15
 
# File 'lib/canon/diff_formatter/by_line/html_formatter.rb', line 13

def html_version
  @html_version
end

Instance Method Details

#format(doc1, doc2) ⇒ String

Format DOM-guided HTML diff

Parameters:

  • doc1 (String) —

    First HTML document

  • doc2 (String) —

    Second HTML document

Returns:

  • (String) —

    Formatted diff



34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
 
# File 'lib/canon/diff_formatter/by_line/html_formatter.rb', line 34

def format(doc1, doc2)
  compute_line_num_width(doc1, doc2)
  # If we have DiffNodes from comparison, use the new pipeline
  if @differences&.any?(Canon::Diff::DiffNode)
    # Check if we should skip based on show_diffs setting
    if should_skip_diff_display?
      return ""
    end

    # Use new pipeline when DiffNodes available
    return format_with_pipeline(doc1, doc2)
  end

  # LEGACY: Fall back to old DOM-based behavior
  # Check if we should show any diffs based on differences array
  if should_skip_diff_display?
    return ""
  end

  require_relative "../../html/data_model"
  require_relative "../../xml/element_matcher"
  require_relative "../../xml/line_range_mapper"
  require_relative "../../pretty_printer/html"

  output = []

  begin
    # Parse to DOM using HTML parser
    root1 = Canon::Html::DataModel.from_html(doc1,
                                             version: @html_version)
    root2 = Canon::Html::DataModel.from_html(doc2,
                                             version: @html_version)

    # Match elements semantically
    matcher = Canon::Xml::ElementMatcher.new
    matches = matcher.match_trees(root1, root2)

    # Pretty-print HTML for line mapping
    pretty_printer = Canon::PrettyPrinter::Html.new(indent: 2)
    pretty1 = pretty_printer.format(doc1)
    pretty2 = pretty_printer.format(doc2)

    # Build line range maps using pretty-printed documents
    mapper1 = Canon::Xml::LineRangeMapper.new(indent: 2)
    mapper2 = Canon::Xml::LineRangeMapper.new(indent: 2)
    map1 = mapper1.build_map(root1, pretty1)
    map2 = mapper2.build_map(root2, pretty2)

    # Use pretty-printed document lines for display
    lines1 = pretty1.split("\n")
    lines2 = pretty2.split("\n")

    # Display diffs based on element matches
    result = format_element_matches(matches, map1, map2, lines1, lines2)
    output << result
  rescue StandardError => e
    # Fall back to simple diff on error
    output << colorize("Warning: DOM parsing failed, using simple diff",
                       :yellow)
    output << colorize("Error: #{e.class}: #{e.message}", :red)

    # Include relevant backtrace lines
    relevant_trace = e.backtrace.select do |line|
      line.include?("canon")
    end.take(3)
    unless relevant_trace.empty?
      output << colorize("Backtrace:", :yellow)
      relevant_trace.each do |line|
        output << colorize("  #{line}", :yellow)
      end
    end

    output << ""
    require_relative "simple_formatter"
    simple = SimpleFormatter.new(
      use_color: @use_color,
      context_lines: @context_lines,
      diff_grouping_lines: @diff_grouping_lines,
      visualization_map: @visualization_map,
    )
    output << simple.format(doc1, doc2)
  end

  output.join("\n")
end

#format_context_from_lines(context, lines1, _lines2) ⇒ Object

Format a context using its DiffLines



169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
 
# File 'lib/canon/diff_formatter/by_line/html_formatter.rb', line 169

def format_context_from_lines(context, lines1, _lines2)
  output = []

  context.lines.each do |diff_line|
    case diff_line.type
    when :unchanged
      line_num = diff_line.line_number + 1
      output << format_unified_line(line_num, line_num, " ",
                                    diff_line.content)
    when :removed
      line_num = diff_line.line_number + 1
      formatting = diff_line.formatting?
      informative = diff_line.informative?

      output << if formatting
                  # Formatting-only removal: [ marker
                  format_unified_line(line_num, nil, "[",
                                      diff_line.content,
                                      theme_color(:formatting,
                                                  :marker) || :black,
                                      formatting: true)
                elsif informative
                  # Informative removal: < marker
                  format_unified_line(line_num, nil, "<",
                                      diff_line.content,
                                      theme_color(:informative,
                                                  :marker) || :blue,
                                      informative: true)
                else
                  # Normative removal: - marker
                  format_unified_line(line_num, nil, "-",
                                      diff_line.content,
                                      theme_color(:removed,
                                                  :marker) || :red)
                end
    when :added
      line_num = diff_line.line_number + 1
      formatting = diff_line.formatting?
      informative = diff_line.informative?

      output << if formatting
                  # Formatting-only addition: ] marker
                  format_unified_line(nil, line_num, "]",
                                      diff_line.content,
                                      theme_color(:formatting,
                                                  :marker) || :white,
                                      formatting: true)
                elsif informative
                  # Informative addition: > marker
                  format_unified_line(nil, line_num, ">",
                                      diff_line.content,
                                      theme_color(:informative,
                                                  :marker) || :cyan,
                                      informative: true)
                else
                  # Normative addition: + marker
                  format_unified_line(nil, line_num, "+",
                                      diff_line.content,
                                      theme_color(:added,
                                                  :marker) || :green)
                end
    when :changed
      line_num = diff_line.line_number + 1
      formatting = diff_line.formatting?
      informative = diff_line.informative?
      old_content = lines1[diff_line.line_number]
      new_content = diff_line.content

      if formatting
        fmt_color = theme_color(:formatting, :marker) || :black
        output << format_unified_line(line_num, nil, "[",
                                      old_content,
                                      fmt_color,
                                      formatting: true)
        output << format_unified_line(nil, line_num, "]",
                                      new_content,
                                      fmt_color,
                                      formatting: true)
      elsif informative
        inf_color = theme_color(:informative, :marker) || :blue
        output << format_unified_line(line_num, nil, "<",
                                      old_content,
                                      inf_color,
                                      informative: true)
        output << format_unified_line(nil, line_num, ">",
                                      new_content,
                                      inf_color,
                                      informative: true)
      else
        output << format_unified_line(line_num, nil, "-",
                                      old_content,
                                      theme_color(:removed,
                                                  :marker) || :red)
        output << format_unified_line(nil, line_num, "+",
                                      new_content,
                                      theme_color(:added,
                                                  :marker) || :green)
      end
    end
  end

  output.join("\n")
end

#format_report(report, doc1, doc2) ⇒ Object

Format a DiffReport for display



141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
 
# File 'lib/canon/diff_formatter/by_line/html_formatter.rb', line 141

def format_report(report, doc1, doc2)
  return "" if report.contexts.empty?

  lines1 = doc1.split("\n")
  lines2 = doc2.split("\n")

  output = []

  # Detect non-ASCII characters
  all_text = (lines1 + lines2).join
  non_ascii = Legend.detect_non_ascii(all_text, @visualization_map)

  # Add Unicode legend if needed
  unless non_ascii.empty?
    output << Legend.build_legend(non_ascii, use_color: @use_color)
    output << ""
  end

  # Format each context
  report.contexts.each_with_index do |context, idx|
    output << "" if idx.positive?
    output << format_context_from_lines(context, lines1, lines2)
  end

  output.join("\n")
end

#format_with_pipeline(doc1, doc2) ⇒ Object

Format using new DiffReportBuilder pipeline



121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
 
# File 'lib/canon/diff_formatter/by_line/html_formatter.rb', line 121

def format_with_pipeline(doc1, doc2)
  require_relative "../../diff/diff_node_mapper"
  require_relative "../../diff/diff_report_builder"

  # Layer 2: Map DiffNodes to DiffLines
  diff_lines = Canon::Diff::DiffNodeMapper.map(@differences, doc1, doc2)

  # Layers 3-5: Build report through pipeline
  report = Canon::Diff::DiffReportBuilder.build(
    diff_lines,
    show_diffs: @show_diffs,
    context_lines: @context_lines,
    grouping_lines: @diff_grouping_lines,
  )

  # Layer 6: Format the report
  format_report(report, doc1, doc2)
end