Class: FECHell

Inherits:
Object
  • Object
show all
Defined in:
lib/fechell.rb

Constant Summary collapse

SEPERATORS = 
{"3.00" => ",",
"5.00" => ",",
"5.1" => ",",
"5.2" => ",",
"5.3" => ",",
"6.1" => "\x1e",
"6.2" => "\x1e",
"6.3" => "\x1e",
"6.4" => "\x1e"
}
@@modules = 
nil

Class Method Summary collapse

Instance Method Summary collapse

Constructor Details

#initialize ⇒ FECHell

Returns a new instance of FECHell.



36
37
38
 
# File 'lib/fechell.rb', line 36

def initialize
	FECHell.load_modules unless @@modules.nil? == false
end

Class Method Details

.load_modules ⇒ Object 



19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
 
# File 'lib/fechell.rb', line 19

def self.load_modules
 	@@modules = {}
	Dir["#{File.dirname(__FILE__)}/defs/*.csv"].each do |filename|
		version = File.basename(filename,".csv")
		
		formats = {}

		FasterCSV.open(filename,"r",:col_sep => ';').each do |line|
			schedule = line[0].gsub(' ','').gsub('Sch','S')
			formats[schedule] = line[1..-1]				
		end

		@@modules[version] = formats

	end
end

Instance Method Details

#fields_for(version, schedule) ⇒ Object 



102
103
104
 
# File 'lib/fechell.rb', line 102

def fields_for(version,schedule)
	@@modules[version][schedule.upcase]
end

#guess_schedule(version, full_schedule) ⇒ Object 



106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
 
# File 'lib/fechell.rb', line 106

def guess_schedule(version,full_schedule)
	schedules = []

	# 1st we look for an exact match
	# otherwise we look for a partial match, taking into account appended returns
	full_schedule.upcase!

	if @@modules[version].keys.index(full_schedule)
		schedules << full_schedule
	else
		@@modules[version].keys.each do |key|
			if full_schedule[0...1] == 'F' # F[number] can have an 'N','A' at the end
				regex = "^#{key}[ANT]?"
			else # TEXT or Schedules. S[Letter][numbers]
				regex = "^#{key}"
			end
			if full_schedule.match(regex)
				schedules << key
			end
		end
	end

   # return the longest match first
	schedules.sort { |l,r| r.size <=> l.size }
end

#guess_seperator(first_line) ⇒ Object 



93
94
95
96
97
98
99
100
 
# File 'lib/fechell.rb', line 93

def guess_seperator(first_line)
	seperator = ","
	if first_line.index(28).nil? == false then
		seperator = "\x1c"
	end

	seperator
end

#header_lines(filename) ⇒ Object 



132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
 
# File 'lib/fechell.rb', line 132

def header_lines(filename)
	seperator,header,form_type,elements = peek_format(filename)	

	csv = FasterCSV.open(filename,"r",:col_sep => seperator)
	
	schedules = guess_schedule(header[:fec_version],form_type)
	
	line = csv.readline
	line = csv.readline
	schedule = line[0]
	schedules1,values1 = process_line(header[:fec_version],schedule,line)
	
	csv.close
	return header[:fec_version],form_type,schedules1[0],values1

end

#peek_format(data) ⇒ Object 



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
 
# File 'lib/fechell.rb', line 41

def peek_format(data)

	header = {}
	parts_raw = []
	first_line = []
	form_type = ''

	lines = []

	begin

		if data.is_a?(Array) then
			lines = data[0..1]
		else
			if data.is_a?(StringIO) then
				file = data
			elsif data.is_a?(String)
				file = File.open(data,"r")
			end
			lines[0] = file.readline
			lines[1] = file.readline
			file.close
		end
		
		line = lines[0]

		seperator = guess_seperator(lines[0])
		parts_raw = FasterCSV.parse(line,:col_sep => seperator)[0]

		header[:record_type] = parts_raw[0]
		header[:ef_type] = parts_raw[1]
		header[:fec_version] = parts_raw[2]
		header[:software_name] = parts_raw[3]
		header[:software_version] = parts_raw[4]
		header[:report_id] = parts_raw[5]
		header[:report_number] = parts_raw[6]

		line = lines[1]
		parts_raw = FasterCSV.parse(line,:col_sep => seperator)[0]

		form_type = parts_raw[0]
		parts_raw.shift
		
	rescue FasterCSV::MalformedCSVError
		header = {}
		parts_raw = []
		first_line = []
		form_type = ''
	end	
	return seperator,header,form_type,parts_raw
end

#process(filename, options = {}) ⇒ Object 



162
163
164
165
166
167
168
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
 
# File 'lib/fechell.rb', line 162

def process(filename,options = {})
		
		seperator,header,form_type,elements = peek_format(filename)		

		schedules = guess_schedule(header[:fec_version],form_type)
					
		if schedules.size == 0 then
			puts "ERROR: #{filename} - type was #{form_type} we found nothing"
		end
		offsets = @@modules[header[:fec_version]][schedules[0]]
		
		begin 
			FasterCSV.open(filename,:col_sep => seperator).each do |line|
				next if line.nil?
				next if line.size == 0
				sch = line[0]

				next unless sch.match('^[STFH]')

				guesses,values = process_line(header[:fec_version],sch,line)

				next if guesses.nil? || guesses.size == 0
				next if values.nil?

				if options[:ignore_schedules]
					match_str = "^#{options[:ignore_schedules].join('|')}"
					next if sch.match(match_str)
				end

				yield [guesses[0],values]

			end
		rescue FasterCSV::MalformedCSVError
			puts "malformed content in file #{filename}"					
		end			
end

#process_line(fec_version, schedule, line) ⇒ Object 



149
150
151
152
153
154
155
156
157
158
159
160
 
# File 'lib/fechell.rb', line 149

def process_line(fec_version,schedule,line)
	guesses = guess_schedule(fec_version,schedule)		
	offsets = @@modules[fec_version][guesses[0]]
	values = {}
	index =0
	offsets.each do |offset|
		values[offset] = line[index]
		index = index + 1
	end

	return guesses,values
end