File: split.awk

package info (click to toggle)
fccexam 1.0.8-1
  • links: PTS, VCS
  • area: main
  • in suites: forky, sid
  • size: 13,088 kB
  • sloc: sh: 172; awk: 114; makefile: 20
file content (170 lines) | stat: -rw-r--r-- 3,919 bytes parent folder | download
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
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
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
119
120
121
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
158
159
160
161
162
163
164
165
166
167
168
169
170
# split question pool file into separate file for each question
# Copyright (C) 2012-2015 John Nogatch <jnogatch@gmail.com>

# discard empty lines
(NF == 0){ next}

# change all tab to space
{gsub( /\t/, " ")}

# remove leading whitespace
{sub( /^[ ]*/, "")}

# remove spurious \r
{gsub( /\r/, "")}

# replace \222 apostrophes
{gsub( /\222/, "\47")}

# replace 3-char hyphen
{gsub( /\342\200\223/, "-")}

# replace \223 quotes
{gsub( /\223/, "\42")}

# replace \224 quotes
{gsub( /\224/, "\42")}

# replace \226 hyphen
{gsub( /\226/, "-")}

# replace \240 space
{gsub( /\240/, " ")}

# replace 3-char exponent leader
{gsub( / \342\200.E/, "^")}

# replace 3-char apostrophes
{gsub( /\342\200\231/, "\47")}

# replace 3-char quotes
{gsub( /\342\200\234/, "\42")}

# replace 3-char quotes
{gsub( /\342\200\235/, "\42")}

# recognize answer/distractor lines
/^[ABCD]\./{
    # output answer/distractor to file
    print $0 > question
    next
    }

# recognize answer/distractor lines (elements 7, 7R)
/^[a-f])/{
    # output answer/distractor to file
    print $0 > question
    next
    }

# anything other than answer/distractor line
{
    close( question)	# avoid leaving too many descriptors open
    question = ""	# no current output file
    }

# recognize answer key lines (elements 1, 3, 8)
/^Answer Key:/{
    sub( /^Answer Key:/, "")
    gsub( /:/, "")
    for (i = NF - 1; i > 0; i -= 2) {
	print $i " " $(i+1) > "answer"
	close( "answer")
	system( "cat " $i " >> answer")
	system( "mv answer " $i)
	}
    next
    }

# recognize answer key lines (element 9)
/^Answers:[^-]+$/{
    sub( /^Answers:/, "")
    gsub( /:/, "")
    for (i = NF - 1; i > 0; i -= 2) {
	print "9-" $i " " $(i+1) > "answer"
	close( "answer")
	system( "cat 9-" $i " >> answer")
	system( "mv answer 9-" $i)
	}
    next
    }

# discard "Section-.:" line (elements 7, 7R)
/^Section-[A-Z]: /{ next}

# discard page number line (elements 7, 7R)
/^- [0-9]+ -$/{ next}

# recognize answer key lines (elements 7, 7R)
/^Answers:[ 	]+[0-9]+[A-Z][0-9]+ - [A-D]/{
    sub( /^Answers:/, "")
    gsub( /-/, "")
    for (i = NF - 1; i > 0; i -= 2) {
	print element "-" $i " " $(i+1) > "answer"
	close( "answer")
	system( "cat " $i " >> answer")
	system( "mv answer " element "-" $i)
	}
    next
    }

# recognize new question (elements 1, 3, 8)
/^[0-9]-[0-9]*/{
    question = $1	# new current output file

    $1 = ""	# remove # from question text
    sub( /^ /, "")

    # output question to file
    print $0 > question
    next
    }

# recognize new question (elements 5 & 6)
/^[0-9][AB][0-9]*$/{
    question = $1	# new current output file

    if (getline != 1) print "unable to read answer line " NR	# read another line & exit if error
    if (NF != 1) print "invalid answer line " NR	# expecting answer

    print question " " $1 > question	# output # & answer to file

    if (getline != 1) print "unable to read question line " NR	# read another line & exit if error
    print $0 > question		# output question text to file
    next
    }

# recognize new question (elements 7, 7R)
/^[0-9]+[A-Z][0-9]+ /{
    question = $1	# new current output file
    sub( /-/, "", question)	# remove "-"
#    print "e7: " $0	# display question # to help correct typos

    $1 = ""		# remove question # from question text
    print $0 > question	# output question text to question file
    next
    }

# recognize new question (element 7)
/^[0-9]+[A-Z][0-9]* */{
    question = "7-" $1	# new current output file

    sub( /^[0-9]+[A-Z][0-9]*/, "")	# remove question #

    print $0 > question	# output complete question text to file
    next
    }

# recognize new question (element 9)
/^[0-9]+[A-Z][0-9]* */{
    question = "9-" $1	# new current output file

    sub( /^[0-9]+[A-Z][0-9]*/, "")	# remove question #

    print $0 > question	# output complete question text to file
    next
    }

# display any line that did not get captured
{ print $0}