Close #71 no parsing for "Unamed clade"

CHANGELOG.md

@@ -4,8 +4,10 @@
 
 ## [v0.12.0]
 
+- Add [#71]: do not parse 'Unamed clade...'.
 - Add [#69]: gnparser as a shared C library.
-- Make dynamic version using ldflags.
+- Add: Make dynamic version using ldflags.
+- Fix [#70]: parse 'Remera cvancarai' correctly.
 
 ## [v0.11.0]
 
@@ -106,6 +108,7 @@ array of names instead of a stream.
 
 This document follows [changelog guidelines]
 
+[v0.12.0]: https://gitlab.com/gogna/gnparser/compare/v0.11.0...v0.12.0
 [v0.11.0]: https://gitlab.com/gogna/gnparser/compare/v0.10.0...v0.11.0
 [v0.10.0]: https://gitlab.com/gogna/gnparser/compare/v0.9.0...v0.10.0
 [v0.9.0]: https://gitlab.com/gogna/gnparser/compare/v0.8.0...v0.9.0
@@ -119,6 +122,9 @@ This document follows [changelog guidelines]
 [v0.6.0]: https://gitlab.com/gogna/gnparser/compare/v0.5.1...v0.6.0
 [v0.5.1]: https://gitlab.com/gogna/gnparser/tree/v0.5.1
 
+[#71]: https://gitlab.com/gogna/gnparser/issues/71
+[#70]: https://gitlab.com/gogna/gnparser/issues/70
+[#69]: https://gitlab.com/gogna/gnparser/issues/69
 [#68]: https://gitlab.com/gogna/gnparser/issues/68
 [#67]: https://gitlab.com/gogna/gnparser/issues/67
 [#66]: https://gitlab.com/gogna/gnparser/issues/66

preprocess/preprocess.go

@@ -19,7 +19,7 @@ var virusRe = regexp.MustCompile(
 		`(alpha|beta)?satellites?)\b`,
 )
 var noParseRe = regexp.MustCompile(
-	`(^(Not|None|Unidentified)[\W_].*|.*[Ii]ncertae\s+[Ss]edis.*` +
+	`(^(Not|None|Un(n?amed|identified))[\W_].*|.*[Ii]ncertae\s+[Ss]edis.*` +
 		`|[Ii]nc\.\s*[Ss]ed\.|phytoplasma\b|plasmids?\b|[^A-Z]RNA[^A-Z]*)`,
 )
 var notesRe = regexp.MustCompile(

testdata/test_data.txt

@@ -3035,6 +3035,16 @@ Notassigned
 Notassigned
 {"parsed":true,"quality":1,"verbatim":"Notassigned","normalized":"Notassigned","canonicalName":{"full":"Notassigned","simple":"Notassigned","stem":"Notassigned"},"details":[{"uninomial":{"value":"Notassigned"}}],"positions":[["uninomial",0,11]],"surrogate":false,"virus":false,"hybrid":false,"bacteria":false,"nameStringId":"8c07b58a-be4e-5c31-871b-cffe36b9860a","parserVersion":"test_version"}
 8c07b58a-be4e-5c31-871b-cffe36b9860a|Notassigned|Notassigned|Notassigned|Notassigned|||1
+
+Unnamed clade
+noparse
+{"parsed":false,"quality":0,"verbatim":"Unnamed clade","surrogate":false,"virus":false,"hybrid":false,"bacteria":false,"nameStringId":"d510b662-0a4d-5678-a1a7-c58b20d25fa0","parserVersion":"test_version"}
+d510b662-0a4d-5678-a1a7-c58b20d25fa0|Unnamed clade||||||0
+
+Unamed clade
+noparse
+{"parsed":false,"quality":0,"verbatim":"Unamed clade","surrogate":false,"virus":false,"hybrid":false,"bacteria":false,"nameStringId":"be6943d3-fa83-5e5d-9515-7cc339473d4d","parserVersion":"test_version"}
+be6943d3-fa83-5e5d-9515-7cc339473d4d|Unamed clade||||||0
 #>
 
 #SECTION: No parsing -- genus with apostrophe<