Module: RubyTube::Parser

Defined in:
lib/rubytube/parser.rb

Class Method Summary collapse

Class Method Details

.find_object_from_startpoint(html, start_point) ⇒ Object 



17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
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
 
# File 'lib/rubytube/parser.rb', line 17

def find_object_from_startpoint(html, start_point)
  html = html[start_point..-1]
  unless ["{", "["].include?(html[0])
    raise HTMLParseError, "Invalid start point. Start of HTML:\n#{html[0..19]}"
  end

  last_char = "{"
  curr_char = nil
  stack = [html[0]]
  i = 1

  context_closers = {
    "{" => "}",
    "[" => "]",
    '"' => '"',
    "/" => "/"
  }

  while i < html.length
    break if stack.empty?

    last_char = curr_char unless [" ", '\n'].include?(curr_char)
    curr_char = html[i]
    curr_context = stack.last

    if curr_char == context_closers[curr_context]
      stack.pop
      i += 1
      next
    end

    if ['"', "/"].include?(curr_context)
      if curr_char == "\\"
        i += 2
        next
      end
    elsif context_closers.keys.include?(curr_char)
      unless curr_char == "/" && !["(", ",", "=", ":", "[", "!", "&", "|", "?", "{", "}", ";"].include?(last_char)
        stack.push(curr_char)
      end
    end

    i += 1
  end

  html[0...i]
end

.parse_for_object(html, preceding_regex) ⇒ Object 



5
6
7
8
9
10
11
12
13
14
15
 
# File 'lib/rubytube/parser.rb', line 5

def parse_for_object(html, preceding_regex)
  regex = Regexp.new(preceding_regex)
  result = regex.match(html)

  if result.nil?
    raise HTMLParseError, "No matches for regex #{preceding_regex}"
  end
  start_index = result.end(0)

  parse_for_object_from_startpoint(html, start_index)
end

.parse_for_object_from_startpoint(html, start_point) ⇒ Object 



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
119
120
 
# File 'lib/rubytube/parser.rb', line 65

def parse_for_object_from_startpoint(html, start_point)
  html = html[start_point..-1]

  unless ["{", "["].include?(html[0])
    raise HTMLParseError, "Invalid start point. Start of HTML:\n#{html[0..19]}"
  end

  # First letter MUST be an open brace, so we put that in the stack,
  # and skip the first character.
  last_char = "{"
  curr_char = nil
  stack = [html[0]]
  i = 1

  context_closers = {
    "{" => "}",
    "[" => "]",
    '"' => '"',
    :"'" => "'",
    "/" => "/" # JavaScript regex
  }

  while i < html.length
    break if stack.empty?

    last_char = curr_char unless [" ", '\n'].include?(curr_char)
    curr_char = html[i]
    curr_context = stack.last

    # If we've reached a context closer, we can remove an element off the stack
    if curr_char == context_closers[curr_context]
      stack.pop
      i += 1
      next
    end
    # Strings and regex expressions require special context handling because they can contain
    # context openers *and* closers
    if ['"', "/"].include?(curr_context)
      # If there's a backslash in a string or regex expression, we skip a character
      if curr_char == "\\"
        i += 2
        next
      end
    elsif context_closers.keys.include?(curr_char)
      # Non-string contexts are when we need to look for context openers.
      unless curr_char == "/" && ["(", ",", "=", ":", "[", "!", "&", "|", "?", "{", "}", ";"].include?(last_char)
        stack << curr_char
      end
      # Slash starts a regular expression depending on context
    end

    i += 1
  end

  html[0..(i - 1)]
end

.throttling_array_split(js_array) ⇒ Object 



122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
 
# File 'lib/rubytube/parser.rb', line 122

def throttling_array_split(js_array)
  results = []
  curr_substring = js_array[1..-1]

  comma_regex = /,/
  func_regex = /function\([^)]*\)/

  until curr_substring.empty?
    if curr_substring.start_with?("function")
      match = func_regex.match(curr_substring)
      match_start = match.begin(0)
      match_end = match.end(0)

      function_text = find_object_from_startpoint(curr_substring, match_end)
      full_function_def = curr_substring[0, match_end + function_text.length]
      results << full_function_def
      curr_substring = curr_substring[full_function_def.length + 1..-1]
    else
      match = comma_regex.match(curr_substring)

      begin
        match_start = match.begin(0)
        match_end = match.end(0)
      rescue NoMethodError
        match_start = curr_substring.length - 1
        match_end = match_start + 1
      end

      curr_el = curr_substring[0, match_start]
      results << curr_el
      curr_substring = curr_substring[match_end..-1]
    end
  end

  results
end