Module: Legion::CLI::Chat::WebFetch

Defined in:
lib/legion/cli/chat/web_fetch.rb

Defined Under Namespace

Classes: FetchError

Constant Summary collapse

MAX_BODY =

1 MB

1_048_576
MAX_REDIRECTS = 
5
TIMEOUT = 
15
CONTEXT_LIMIT =

chars injected into conversation

12_000

Class Method Summary collapse

Class Method Details

.clean_whitespace(text) ⇒ Object 



267
268
269
270
271
272
273
274
275
 
# File 'lib/legion/cli/chat/web_fetch.rb', line 267

def clean_whitespace(text)
  text = text.gsub(' ', ' ')
             .gsub('&', '&')
             .gsub('&lt;', '<')
             .gsub('&gt;', '>')
             .gsub('&quot;', '"')
             .gsub('&#39;', "'")
  text.gsub(/\n{3,}/, "\n\n").gsub(/ +/, ' ').strip
end

.convert_blocks!(text) ⇒ Object 



242
243
244
245
246
247
248
249
 
# File 'lib/legion/cli/chat/web_fetch.rb', line 242

def convert_blocks!(text)
  replace_tag_blocks!(text, 'pre') { |inner| "\n```\n#{inner}\n```\n" }
  replace_tag_blocks!(text, 'blockquote') { |inner| "\n> #{inner}\n" }
  replace_open_tags!(text, 'p', "\n\n")
  replace_close_tags!(text, 'p', "\n")
  replace_self_closing!(text, 'br', "\n")
  replace_self_closing!(text, 'hr', "\n---\n")
end

.convert_formatting!(text) ⇒ Object 



236
237
238
239
240
 
# File 'lib/legion/cli/chat/web_fetch.rb', line 236

def convert_formatting!(text)
  %w[b strong].each { |t| replace_tag_blocks!(text, t) { |inner| "**#{inner}**" } }
  %w[i em].each { |t| replace_tag_blocks!(text, t) { |inner| "*#{inner}*" } }
  replace_tag_blocks!(text, 'code') { |inner| "`#{inner}`" }
end

.convert_headings!(text) ⇒ Object 



183
184
185
186
187
188
 
# File 'lib/legion/cli/chat/web_fetch.rb', line 183

def convert_headings!(text)
  (1..6).each do |n|
    prefix = '#' * n
    replace_tag_blocks!(text, "h#{n}") { |inner| "\n#{prefix} #{inner}\n" }
  end
end

.convert_links!(text) ⇒ Object 



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
 
# File 'lib/legion/cli/chat/web_fetch.rb', line 190

def convert_links!(text)
  result = String.new
  pos = 0
  while pos < text.length
    open_idx = text.index(/<a[\s>]/mi, pos)
    break unless open_idx

    close_idx = text.index(%r{</a\s*>}mi, open_idx)
    unless close_idx
      result << text[pos..]
      pos = text.length
      break
    end

    result << text[pos...open_idx]

    tag_end = text.index('>', open_idx)
    if tag_end && tag_end < close_idx
      tag = text[open_idx..tag_end]
      href = tag[/href=["']([^"']*)["']/i, 1]
      inner = text[(tag_end + 1)...close_idx]
      result << if href
                  "[#{inner}](#{href})"
                else
                  inner
                end
    else
      # Malformed opening tag — preserve the inner text up to the closing tag
      result << text[open_idx...close_idx]
    end

    close_end = text.index('>', close_idx)
    pos = close_end ? close_end + 1 : close_idx + 4
  end
  result << text[pos..] if pos < text.length
  text.replace(result)
end

.convert_lists!(text) ⇒ Object 



228
229
230
231
232
233
234
 
# File 'lib/legion/cli/chat/web_fetch.rb', line 228

def convert_lists!(text)
  replace_tag_blocks!(text, 'li') { |inner| "\n- #{inner}" }
  replace_open_tags!(text, 'ul', "\n")
  replace_close_tags!(text, 'ul', "\n")
  replace_open_tags!(text, 'ol', "\n")
  replace_close_tags!(text, 'ol', "\n")
end

.fetch(url) ⇒ Object 



20
21
22
23
24
25
26
27
28
29
30
31
 
# File 'lib/legion/cli/chat/web_fetch.rb', line 20

def fetch(url)
  uri = parse_uri(url)
  body, content_type = follow_redirects(uri)

  text = if html?(content_type)
           html_to_markdown(body)
         else
           body
         end

  truncate(text.strip, CONTEXT_LIMIT)
end

.follow_redirects(uri, limit = MAX_REDIRECTS) ⇒ Object 



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
 
# File 'lib/legion/cli/chat/web_fetch.rb', line 43

def follow_redirects(uri, limit = MAX_REDIRECTS)
  raise FetchError, 'Too many redirects' if limit.zero?

  http = Net::HTTP.new(uri.host, uri.port)
  http.use_ssl = (uri.scheme == 'https')
  http.open_timeout = TIMEOUT
  http.read_timeout = TIMEOUT

  request = Net::HTTP::Get.new(uri.request_uri)
  request['User-Agent'] = 'LegionIO/1.0 (CLI web fetch)'
  request['Accept']     = 'text/html, text/plain, application/json'

  response = http.request(request)

  case response
  when Net::HTTPRedirection
    location = response['location']
    new_uri = URI.parse(location)
    new_uri = URI.join(uri, location) unless new_uri.host
    follow_redirects(new_uri, limit - 1)
  when Net::HTTPSuccess
    body = response.body&.dup&.force_encoding('UTF-8') || ''
    raise FetchError, "Response too large (#{body.bytesize} bytes)" if body.bytesize > MAX_BODY

    [body, response['content-type']]
  else
    raise FetchError, "HTTP #{response.code}: #{response.message}"
  end
rescue SocketError => e
  raise FetchError, "Connection failed: #{e.message}"
rescue Net::OpenTimeout, Net::ReadTimeout
  raise FetchError, "Request timed out (#{TIMEOUT}s)"
rescue OpenSSL::SSL::SSLError => e
  raise FetchError, "SSL error: #{e.message}"
end

.html?(content_type) ⇒ Boolean

Returns:

  • (Boolean) 


79
80
81
 
# File 'lib/legion/cli/chat/web_fetch.rb', line 79

def html?(content_type)
  content_type&.include?('text/html') || false
end

.html_to_markdown(html) ⇒ Object 



83
84
85
86
87
88
89
90
91
92
93
 
# File 'lib/legion/cli/chat/web_fetch.rb', line 83

def html_to_markdown(html)
  text = html.dup
  strip_invisible!(text)
  convert_headings!(text)
  convert_links!(text)
  convert_lists!(text)
  convert_formatting!(text)
  convert_blocks!(text)
  strip_remaining_tags!(text)
  clean_whitespace(text)
end

.parse_uri(url) ⇒ Object 



33
34
35
36
37
38
39
40
41
 
# File 'lib/legion/cli/chat/web_fetch.rb', line 33

def parse_uri(url)
  url = "https://#{url}" unless url.match?(%r{\Ahttps?://})
  uri = URI.parse(url)
  raise FetchError, "Invalid URL: #{url}" unless uri.is_a?(URI::HTTP)

  uri
rescue URI::InvalidURIError
  raise FetchError, "Invalid URL: #{url}"
end

.replace_close_tags!(text, tag, replacement) ⇒ Object 



161
162
163
164
165
166
167
168
169
 
# File 'lib/legion/cli/chat/web_fetch.rb', line 161

def replace_close_tags!(text, tag, replacement)
  pat = %r{</#{tag}\s*>}mi
  loop do
    match = pat.match(text)
    break unless match

    text[match.begin(0)..(match.end(0) - 1)] = replacement
  end
end

.replace_open_tags!(text, tag, replacement) ⇒ Object 



149
150
151
152
153
154
155
156
157
158
159
 
# File 'lib/legion/cli/chat/web_fetch.rb', line 149

def replace_open_tags!(text, tag, replacement)
  loop do
    idx = text.index(/<#{tag}[\s>]/mi)
    break unless idx

    close = text.index('>', idx)
    break unless close

    text[idx..close] = replacement
  end
end

.replace_self_closing!(text, tag, replacement) ⇒ Object 



171
172
173
174
175
176
177
178
179
180
181
 
# File 'lib/legion/cli/chat/web_fetch.rb', line 171

def replace_self_closing!(text, tag, replacement)
  loop do
    idx = text.index(%r{<#{tag}[\s>/]}mi)
    break unless idx

    close = text.index('>', idx)
    break unless close

    text[idx..close] = replacement
  end
end

.replace_tag_blocks!(text, tag) ⇒ Object 



129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
 
# File 'lib/legion/cli/chat/web_fetch.rb', line 129

def replace_tag_blocks!(text, tag)
  loop do
    open_idx = text.index(/<#{tag}[\s>]/mi)
    break unless open_idx

    tag_end = text.index('>', open_idx)
    break unless tag_end

    close_pat = %r{</#{tag}\s*>}mi
    close_match = close_pat.match(text, tag_end)
    if close_match
      inner = text[(tag_end + 1)...close_match.begin(0)]
      replacement = yield(inner)
      text[open_idx..(close_match.end(0) - 1)] = replacement
    else
      text[open_idx..] = ''
    end
  end
end

.strip_html_comments!(text) ⇒ Object 



100
101
102
103
104
105
106
107
108
109
110
111
112
 
# File 'lib/legion/cli/chat/web_fetch.rb', line 100

def strip_html_comments!(text)
  loop do
    open_idx = text.index('<!--')
    break unless open_idx

    close_idx = text.index('-->', open_idx + 4)
    if close_idx
      text[open_idx..(close_idx + 2)] = ''
    else
      text[open_idx..] = ''
    end
  end
end

.strip_invisible!(text) ⇒ Object 



95
96
97
98
 
# File 'lib/legion/cli/chat/web_fetch.rb', line 95

def strip_invisible!(text)
  %w[script style nav footer].each { |tag| strip_tag_blocks!(text, tag) }
  strip_html_comments!(text)
end

.strip_remaining_tags!(text) ⇒ Object 



251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
 
# File 'lib/legion/cli/chat/web_fetch.rb', line 251

def strip_remaining_tags!(text)
  result = String.new(capacity: text.length)
  pos = 0
  while pos < text.length
    open_idx = text.index('<', pos)
    unless open_idx
      result << text[pos..]
      break
    end
    result << text[pos...open_idx]
    close_idx = text.index('>', open_idx)
    pos = close_idx ? close_idx + 1 : text.length
  end
  text.replace(result)
end

.strip_tag_blocks!(text, tag) ⇒ Object 



114
115
116
117
118
119
120
121
122
123
124
125
126
127
 
# File 'lib/legion/cli/chat/web_fetch.rb', line 114

def strip_tag_blocks!(text, tag)
  loop do
    open_idx = text.index(/<#{tag}[\s>]/mi)
    break unless open_idx

    close_pat = %r{</#{tag}\s*>}mi
    close_match = close_pat.match(text, open_idx)
    if close_match
      text[open_idx..(close_match.end(0) - 1)] = ''
    else
      text[open_idx..] = ''
    end
  end
end

.truncate(text, limit) ⇒ Object 



277
278
279
280
281
 
# File 'lib/legion/cli/chat/web_fetch.rb', line 277

def truncate(text, limit)
  return text if text.length <= limit

  text[0, limit] + "\n\n[... truncated at #{limit} characters]"
end