split: add flag --ignore-case. #462

CHANGELOG.md

@@ -4,6 +4,8 @@
         - Fix a big introduced in v2.7.0. When more than one pairs of primers are given, only the last one is used. [#457](https://github.com/shenwei356/seqkit/issues/457)
     - `seqkit translate`:
         - Add option `-e/--skip-translate-errors` to skip translate error and output empty sequence. [#458](https://github.com/shenwei356/seqkit/pull/458)
+    - `seqkit split`:
+        - Add flag `--ignore-case` for `-i/--by-id`. [#462](https://github.com/shenwei356/seqkit/issues/462)
 - [SeqKit v2.8.1](https://github.com/shenwei356/seqkit/releases/tag/v2.8.1) - 2024-04-07
 [![Github Releases (by Release)](https://img.shields.io/github/downloads/shenwei356/seqkit/v2.8.1/total.svg)](https://github.com/shenwei356/seqkit/releases/tag/v2.8.1)
     - `seqkit sana`:

doc/docs/usage.md

@@ -2588,6 +2588,7 @@ Flags:
   -e, --extension string          set output file extension, e.g., ".gz", ".xz", or ".zst"
   -f, --force                     overwrite output directory
   -h, --help                      help for split
+      --ignore-case               ignore case when using -i/--by-id
   -k, --keep-temp                 keep temporary FASTA and .fai file when using 2-pass mode
   -O, --out-dir string            output directory (default value is $infile.split)
   -2, --two-pass                  two-pass mode read files twice to lower memory usage. (only for FASTA

seqkit/cmd/split.go

@@ -94,6 +94,7 @@ Examples:
 		part := getFlagNonNegativeInt(cmd, "by-part")
 
 		byID := getFlagBool(cmd, "by-id")
+		ignoreCase := getFlagBool(cmd, "ignore-case")
 		region := getFlagString(cmd, "by-region")
 		twoPass := getFlagBool(cmd, "two-pass")
 		updateFaidx := getFlagBool(cmd, "update-faidx")
@@ -619,6 +620,9 @@ Examples:
 						renameFileExt = false
 					}
 					id = string(record.ID)
+					if ignoreCase {
+						id = strings.ToLower(id)
+					}
 					if _, ok := recordsByID[id]; !ok {
 						recordsByID[id] = []*fastx.Record{}
 					}
@@ -718,6 +722,9 @@ Examples:
 			idsMap := make(map[string][]string)
 			for _, ID := range IDs {
 				id := string(fastx.ParseHeadID(idRe, []byte(ID)))
+				if ignoreCase {
+					id = strings.ToLower(id)
+				}
 				if _, ok := idsMap[id]; !ok {
 					idsMap[id] = []string{}
 				}
@@ -1020,6 +1027,7 @@ func init() {
 	splitCmd.Flags().IntP("by-size", "s", 0, "split sequences into multi parts with N sequences")
 	splitCmd.Flags().IntP("by-part", "p", 0, "split sequences into N parts")
 	splitCmd.Flags().BoolP("by-id", "i", false, "split squences according to sequence ID")
+	splitCmd.Flags().BoolP("ignore-case", "", false, "ignore case when using -i/--by-id")
 	splitCmd.Flags().StringP("by-region", "r", "", "split squences according to subsequence of given region. "+
 		`e.g 1:12 for first 12 bases, -12:-1 for last 12 bases. type "seqkit split -h" for more examples`)
 	splitCmd.Flags().BoolP("two-pass", "2", false, "two-pass mode read files twice to lower memory usage. (only for FASTA format)")