基本完成

This commit is contained in:
qaqland 2022-01-04 16:59:37 +08:00
parent 20c23128ee
commit c449b57a80
3 changed files with 39 additions and 19 deletions

View file

@ -6,5 +6,5 @@ sequence combination tool written in Golang
``` ```
parser xxx.fas parser xxx.fas
parser xxx.fas yyy.fas parser xxx.fas yyy.fas
parser -o 123 xxx.fas // todo parser -o export.nex xxx.fas yyy.fas
``` ```

View file

@ -36,13 +36,13 @@ func main() {
file_names := flag.Args() // []string{"foo", "bar"} file_names := flag.Args() // []string{"foo", "bar"}
fmt.Println("[ export here ]", *file_export) fmt.Println("[ export here ]", *file_export)
// 遍历文件 // 遍历文件得到基本数据
sum_nex := make([]dna, 0, 5) sum_nex := make([]dna, 0, 5)
for k, v := range file_names { for k, v := range file_names {
i, j := fas_parser.Fas_parser(v) i, j := fas_parser.Fas_parser(v)
new_nex := dna{v, i, j} new_nex := dna{v, i, j}
sum_nex = append(sum_nex, new_nex) sum_nex = append(sum_nex, new_nex)
fmt.Println("[ working ]", k+1, v) fmt.Println("[ working A ]", k+1, v)
} }
// 整合若干文件的统计 // 整合若干文件的统计
@ -54,29 +54,45 @@ func main() {
f = sum_charset[k-1].To f = sum_charset[k-1].To
} }
t := f + v.count t := f + v.count
fmt.Println("[ working B ]", n, f, t)
new_charset := charset{n, f, t} new_charset := charset{n, f, t}
sum_charset = append(sum_charset, new_charset) sum_charset = append(sum_charset, new_charset)
} }
fmt.Println(sum_charset) // fmt.Println(sum_charset)
// dna 的整合 // dna 的整合
seq := sum_nex[0].min_dna ntax := 0
ntax := 0 // 待修补
nchar := sum_charset[len(sum_charset)-1].To nchar := sum_charset[len(sum_charset)-1].To
sum_dna := make(map[string][]string)
for k, v := range sum_nex { for k, v := range sum_nex {
if k == 0 { for k1 := range v.min_dna {
continue _, has := sum_dna[k1]
if !has {
sum_dna[k1] = make([]string, len(sum_charset))
} }
last_count := sum_nex[k-1].count }
for k1, v1 := range v.min_dna { ntax = k
if _, ok := seq[k1]; ok { }
seq[k1] = seq[k1] + v1 for k, v := range sum_nex {
for _, v1 := range v.min_dna {
for k2 := range sum_dna {
if _, ok := v.min_dna[k2]; ok {
sum_dna[k2][k] = v1
} else { } else {
seq[k1] = seq[k1] + strings.Repeat("?", last_count) sum_dna[k2][k] = strings.Repeat("?", v.count)
} }
} }
} }
last_data := tmpl_data{ntax, nchar, seq, sum_charset} }
// fmt.Println(sum_dna)
matrix := make(map[string]string, ntax)
for k := range sum_dna {
matrix[k] = strings.Join(sum_dna[k], "")
}
// 准备发射到模板的数据
last_data := tmpl_data{ntax, nchar, matrix, sum_charset}
// fmt.Println(last_data) // fmt.Println(last_data)
// 读取模板 // 读取模板

View file

@ -4,13 +4,17 @@ const Nex_tmpl = `#NEXUS
BEGIN DATA; BEGIN DATA;
DIMENSIONS NTAX={{ .Ntax }} NCHAR={{ .Nchar }}; DIMENSIONS NTAX={{ .Ntax }} NCHAR={{ .Nchar }};
FORMAT DATATYPE=DNA GAP=- MISSING=? ; #DATATYPE={} FORMAT DATATYPE=DNA GAP=- MISSING=? ; #DATATYPE={}
MATRIX{{ range $k, $v := .Matrix }} MATRIX
{{- range $k, $v := .Matrix }}
'{{ $k }}' {{ $v }}{{ end }} '{{ $k }}' {{ $v }}{{ end }}
; ;
END; END;
BEGIN SETS;{{ range $_, $i := .Charset }} BEGIN SETS;
CHARSET {{ .Name }} = {{ .From }}-{{ .To }};{{ end }} {{- range $_, $i := .Charset }}
CHARSET {{ $i.Name }} = {{ $i.From }}-{{ $i.To }};
{{- end }}
END; END;
` `
// 最后那个 $i 好像有问题 // 最后那个 $i 好像有问题
// {{/* $k| printf "%-40s" */}}