fix the default option value of --field-accession-re, #65

shenwei356 · Sep 19, 2022 · a93923a · a93923a
1 parent fda834a
commit a93923a
Show file tree

Hide file tree

Showing 3 changed files with 21 additions and 16 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -5,7 +5,9 @@
         - do not panic for invalid TaxIds, e.g., the column name, when using `-I--taxid-field`.
     - `taxonkit create-taxdump`: 
         - fix merged.dmp and delnodes.dmp. Thanks to @apcamargo ! [gtdb-taxdump/issues/2](https://github.com/shenwei356/gtdb-taxdump/issues/2).
-        - fix bug of handling non-GTDB data when using `-A/--field-accession` and no rank names given.
+        - fix bug of handling non-GTDB data when using `-A/--field-accession` and no rank names given:
+          the colname of the accession column would be treated as one of the ranks, which messed up all the ranks.
+        - fix the default option value of `--field-accession-re` which wrongly remove prefix like `Sp_`. [#65](https://github.com/shenwei356/taxonkit/issues/65)
     - `taxonkit list`:
         - fix warning message of merged taxids.
 - [TaxonKit v0.12.0](https://github.com/shenwei356/taxonkit/releases/tag/v0.12.0)

diff --git a/doc/docs/usage.md b/doc/docs/usage.md
@@ -1533,20 +1533,19 @@ Examples:
             | sed 1d \
             > mgv.tsv
 
-        $ taxonkit create-taxdump mgv.tsv --out-dir mgv --force -A 5 -R order,family,genus,species,contig
-        16:45:40.555 [WARN] --field-accession-re failed to extract genome accession, the origninal value is used instead. e.g., MGV-GENOME-0231225
-        16:45:40.817 [INFO] 189680 records saved to mgv/taxid.map
-        16:45:40.846 [INFO] 54224 records saved to mgv/nodes.dmp
-        16:45:40.864 [INFO] 54224 records saved to mgv/names.dmp
-        16:45:40.864 [INFO] 0 records saved to mgv/merged.dmp
-        16:45:40.864 [INFO] 0 records saved to mgv/delnodes.dmp
+        $ taxonkit create-taxdump mgv.tsv --out-dir mgv --force -A 5 -R order,family,genus,species
+        23:33:18.098 [INFO] 189680 records saved to mgv/taxid.map
+        23:33:18.131 [INFO] 58102 records saved to mgv/nodes.dmp
+        23:33:18.150 [INFO] 58102 records saved to mgv/names.dmp
+        23:33:18.150 [INFO] 0 records saved to mgv/merged.dmp
+        23:33:18.150 [INFO] 0 records saved to mgv/delnodes.dmp
         
         $ head -n 5 mgv/taxid.map 
-        MGV-GENOME-0364295      3108345579
-        MGV-GENOME-0364296      2356405276
-        MGV-GENOME-0364303      1099424244
-        MGV-GENOME-0364311      4037644503
-        MGV-GENOME-0364312      452745976
+        MGV-GENOME-0364295      677052301
+        MGV-GENOME-0364296      677052301
+        MGV-GENOME-0364303      1414406025
+        MGV-GENOME-0364311      1849074420
+        MGV-GENOME-0364312      2074846424
         
         $ echo 677052301 | taxonkit lineage --data-dir mgv/ 
         677052301       Caudovirales;crAss-phage;OTU-61123
@@ -1579,7 +1578,6 @@ Examples:
         # the first column as accession
         $ taxonkit create-taxdump -A 1 example/taxonomy.tsv -O example/taxdump
         16:31:31.828 [INFO] I will use the first row of input as rank names
-        16:31:31.841 [WARN] --field-accession-re failed to extract genome accession, the origninal value is used instead. e.g., GCF_000742135.1
         16:31:31.843 [INFO] 13 records saved to example/taxdump/taxid.map
         16:31:31.843 [INFO] 39 records saved to example/taxdump/nodes.dmp
         16:31:31.843 [INFO] 39 records saved to example/taxdump/names.dmp

diff --git a/taxonkit/cmd/create-taxdump.go b/taxonkit/cmd/create-taxdump.go
@@ -105,8 +105,14 @@ Attentions:
 
 		var err error
 
+		isGTDB := getFlagBool(cmd, "gtdb")
+
 		reGenomeIDStr := getFlagString(cmd, "field-accession-re")
 
+		if isGTDB && !cmd.Flags().Lookup("field-accession-re").Changed {
+			reGenomeIDStr = `^\w\w_(.+)$`
+		}
+
 		var reGenomeID *regexp.Regexp
 		if reGenomeIDStr != "" {
 			if !regexp.MustCompile(`\(.+\)`).MatchString(reGenomeIDStr) {
@@ -119,7 +125,6 @@ Attentions:
 			}
 		}
 
-		isGTDB := getFlagBool(cmd, "gtdb")
 		reGTDBStr := getFlagString(cmd, "gtdb-re-subs")
 
 		var reGTDBsubspe *regexp.Regexp
@@ -906,7 +911,7 @@ func init() {
 	RootCmd.AddCommand(createTaxDumpCmd)
 
 	createTaxDumpCmd.Flags().IntP("field-accession", "A", 0, "field index of assembly accession (genome ID), for outputting taxid.map")
-	createTaxDumpCmd.Flags().StringP("field-accession-re", "", `^\w\w_(.+)$`, `regular expression to extract assembly accession`)
+	createTaxDumpCmd.Flags().StringP("field-accession-re", "", `^(.+)$`, `regular expression to extract assembly accession`)
 	createTaxDumpCmd.Flags().BoolP("field-accession-as-subspecies", "S", false, "treate the accession as subspecies rank")
 	// -------------------------------------------------------------------