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
|
#!/usr/bin/awk -f
#**************************************************************************
#
# 2011/11/12 use OFS as output field separator
# e.g. gawk -f csv.awk -v OFS=, myfile.csv
#
# This file is in the public domain.
#
# For more information email LoranceStinson+csv@gmail.com.
# Or see http://lorance.freeshell.org/csv/
#
# Parse a CSV string into an array.
# The number of fields found is returned.
# In the event of an error a negative value is returned and csverr is set to
# the error. See below for the error values.
#
# Parameters:
# string = The string to parse.
# csv = The array to parse the fields into.
# sep = The field separator character. Normally ,
# quote = The string quote character. Normally "
# escape = The quote escape character. Normally "
# newline = Handle embedded newlines. Provide either a newline or the
# string to use in place of a newline. If left empty embedded
# newlines cause an error.
# trim = When true spaces around the separator are removed.
# This affects parsing. Without this a space between the
# separator and quote result in the quote being ignored.
#
# These variables are private:
# fields = The number of fields found thus far.
# pos = Where to pull a field from the string.
# strtrim = True when a string is found so we know to remove the quotes.
#
# Error conditions:
# -1 = Unable to read the next line.
# -2 = Missing end quote.
# -3 = Missing separator.
#
# Notes:
# The code assumes that every field is preceded by a separator, even the
# first field. This makes the logic much simpler, but also requires a
# separator be prepended to the string before parsing.
#**************************************************************************
function parse_csv(string,csv,sep,quote,escape,newline,trim, fields,pos,strtrim) {
# Make sure there is something to parse.
if (length(string) == 0) return 0;
string = sep string; # The code below assumes ,FIELD.
fields = 0; # The number of fields found thus far.
while (length(string) > 0) {
# Remove spaces after the separator if requested.
if (trim && substr(string, 2, 1) == " ") {
if (length(string) == 1) return fields;
string = substr(string, 2);
continue;
}
strtrim = 0; # Used to trim quotes off strings.
# Handle a quoted field.
if (substr(string, 2, 1) == quote) {
pos = 2;
do {
pos++
if (pos != length(string) &&
substr(string, pos, 1) == escape &&
(substr(string, pos + 1, 1) == quote ||
substr(string, pos + 1, 1) == escape)) {
# Remove escaped quote characters.
string = substr(string, 1, pos - 1) substr(string, pos + 1);
} else if (substr(string, pos, 1) == quote) {
# Found the end of the string.
strtrim = 1;
} else if (newline && pos >= length(string)) {
# Handle embedded newlines if requested.
if (getline == -1) {
csverr = "Unable to read the next line.";
return -1;
}
string = string newline $0;
}
} while (pos < length(string) && strtrim == 0)
if (strtrim == 0) {
csverr = "Missing end quote.";
return -2;
}
} else {
# Handle an empty field.
if (length(string) == 1 || substr(string, 2, 1) == sep) {
csv[fields] = "";
fields++;
if (length(string) == 1)
return fields;
string = substr(string, 2);
continue;
}
# Search for a separator.
pos = index(substr(string, 2), sep);
# If there is no separator the rest of the string is a field.
if (pos == 0) {
csv[fields] = substr(string, 2);
fields++;
return fields;
}
}
# Remove spaces after the separator if requested.
if (trim && pos != length(string) && substr(string, pos + strtrim, 1) == " ") {
trim = strtrim
# Count the number fo spaces found.
while (pos < length(string) && substr(string, pos + trim, 1) == " ") {
trim++
}
# Remove them from the string.
string = substr(string, 1, pos + strtrim - 1) substr(string, pos + trim);
# Adjust pos with the trimmed spaces if a quotes string was not found.
if (!strtrim) {
pos -= trim;
}
}
# Make sure we are at the end of the string or there is a separator.
if ((pos != length(string) && substr(string, pos + 1, 1) != sep)) {
csverr = "Missing separator.";
return -3;
}
# Gather the field.
csv[fields] = substr(string, 2 + strtrim, pos - (1 + strtrim * 2));
fields++;
# Remove the field from the string for the next pass.
string = substr(string, pos + 1);
}
return fields;
}
BEGIN {
if (osep == "") osep = ",";
OFS = osep;
if (isep == "") isep = ",";
if (quote == "") quote = "\"";
if (escape == "") escape = "\"";
if (newline == "") newline = "\\n";
if (trim == "") trim = 1;
}
{
num_fields = parse_csv($0, csv, isep, quote, escape, newline, trim);
if (num_fields < 0) {
printf "ERROR: %s (%d) -> %s\n", csverr, num_fields, $0;
} else {
printf "%s", csv[0]
for (i = 1;i < num_fields;i++) {
printf "%s%s", OFS, csv[i];
}
printf "\n";
}
}
|
