/
csvmung.go
169 lines (151 loc) · 3.53 KB
/
csvmung.go
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
package main
import (
"encoding/csv"
"errors"
"flag"
"fmt"
"github.com/hlawrenz/csvmung/filters"
"io"
"os"
"regexp"
"strconv"
"unicode/utf8"
)
var inputFn string
var outputFn string
var inputSep string
var outputSep string
var lazyQuotes bool
var strictLen bool
func init() {
flag.StringVar(&inputFn, "i", "", "Input file. STDIN used if unspecified.")
flag.StringVar(&outputFn, "o", "", "Output file. STDOUT used if unspecified.")
flag.StringVar(&inputSep, "is", ",", "Input separator. Defaults to comma.")
flag.StringVar(&outputSep, "os", ",", "Output separator. Defaults to comma.")
flag.BoolVar(&lazyQuotes, "lazy-quote", false, "Allow lazy quotes in input.")
flag.BoolVar(&strictLen, "strict-len", false, "Different length rows treates as an error.")
}
func readCsv(ch chan []string) {
var reader *csv.Reader
if inputFn == "" {
reader = csv.NewReader(os.Stdin)
} else {
file, err := os.Open(inputFn)
if err != nil {
fmt.Println("Error:", err)
os.Exit(1)
}
defer file.Close()
reader = csv.NewReader(file)
}
if !strictLen {
reader.FieldsPerRecord = -1
}
r, _ := utf8.DecodeRuneInString(inputSep)
reader.Comma = r
reader.LazyQuotes = lazyQuotes
for {
record, err := reader.Read()
if err == io.EOF {
close(ch)
break
} else if err != nil {
fmt.Println("Error:", err)
close(ch)
break
}
ch <- record
}
}
func writeCsv(ch chan []string) {
var writer *csv.Writer
if outputFn == "" {
writer = csv.NewWriter(os.Stdout)
} else {
file, err := os.Create(outputFn)
if err != nil {
fmt.Println("Error:", err)
os.Exit(1)
}
defer file.Close()
writer = csv.NewWriter(file)
}
r, _ := utf8.DecodeRuneInString(outputSep)
writer.Comma = r
for row := range ch {
err := writer.Write(row)
if err != nil {
fmt.Println("Error:", err)
close(ch)
return
}
}
writer.Flush()
}
func buildFilters() (f []filters.Filterer, err error) {
var fs []filters.Filterer
re := regexp.MustCompile(":")
args := flag.Args()
for a := range args {
filterArg := re.Split(args[a], -1)
filterName := filterArg[0]
switch filterName {
case "re":
column, err := strconv.Atoi(filterArg[1])
if err != nil {
return nil, errors.New("Bad column argument " + filterArg[1])
}
newFilter := filters.RegexFilterer{column, regexp.MustCompile(filterArg[2])}
fs = append(fs, newFilter)
case "split":
column, err := strconv.Atoi(filterArg[1])
if err != nil {
return nil, errors.New("Bad column argument " + filterArg[1])
}
newFilter := filters.SplitFilterer{column, regexp.MustCompile(filterArg[2])}
fs = append(fs, newFilter)
case "uniq":
column, err := strconv.Atoi(filterArg[1])
if err != nil {
return nil, errors.New("Bad column argument " + filterArg[1])
}
newFilter := filters.UniqFilterer{column}
fs = append(fs, newFilter)
case "cols":
var cols []interface{}
for _, col := range filterArg[1:] {
v, err := strconv.Atoi(col)
if err != nil {
cols = append(cols, col)
} else {
cols = append(cols, v)
}
}
newFilter := filters.ColFilterer{cols}
fs = append(fs, newFilter)
default:
fmt.Println("Unknown filter type")
}
}
return fs, nil
}
func main() {
flag.Parse()
inCh := make(chan []string)
go readCsv(inCh)
filters, err := buildFilters()
if err != nil {
fmt.Println(err)
os.Exit(1)
}
if len(filters) < 1 {
fmt.Println("You must specify at least one filter")
os.Exit(1)
}
var outCh chan []string
for filter := range filters {
outCh = filters[filter].Filter(inCh)
inCh = outCh
}
writeCsv(outCh)
}