Merge pull request #1615 from nextstrain/james/watronfire-spaces-in-b…

…east-annotations

Allow spaces in BEAST annotations mk2

CHANGES.md

@@ -11,11 +11,13 @@
 * filter: Improved warning and error messages in the case of missing columns. [#1604] (@victorlin)
 * merge: Any user-customized `~/.sqliterc` file is now ignored so it doesn't break `augur merge`'s internal use of SQLite. [#1608][] (@tsibley)
 * merge: Non-id columns in metadata inputs that would conflict with the output id column are now forbidden and will cause an error if present.  Previously they would overwrite values in the output id column, causing incorrect output. [#1593][] (@tsibley)
+* import: Spaces in BEAST MCC tree annotations (for example, from a discrete state reconstruction) no longer break `augur import beast`'s parsing. [#1610][] (@watronfire)
 
 [#1593]: https://github.com/nextstrain/augur/pull/1593
 [#1594]: https://github.com/nextstrain/augur/pull/1594
 [#1604]: https://github.com/nextstrain/augur/pull/1604
 [#1608]: https://github.com/nextstrain/augur/pull/1608
+[#1610]: https://github.com/nextstrain/augur/pull/1610
 
 ## 25.3.0 (22 August 2024)
 

augur/import_/beast.py

@@ -116,15 +116,15 @@ def parse_beast_tree(data, tipMap, verbose=False):
                 print('%d adding multitype node %s'%(i,multitypeNode.group(1)))
             i+=len(multitypeNode.group(1))
 
-        commentBlock=re.match(r'(\:)*\[(&[A-Za-z\_\-{}\,0-9\.\%=\"\'\+!#]+)\]',data[i:])## look for MCC comments
+        commentBlock=re.match(r'(\:)*\[(&[A-Za-z\_\-{}\,0-9\.\%=\"\'\+ !#]+)\]',data[i:])## look for MCC comments
         if commentBlock is not None:
             if verbose==True:
                 print('%d comment: %s'%(i,commentBlock.group(2)))
             comment=commentBlock.group(2)
             numerics=re.findall(r'[,&][A-Za-z\_\.0-9]+=[0-9\-Ee\.]+',comment) ## find all entries that have values as floats
-            strings=re.findall(r'[,&][A-Za-z\_\.0-9]+=["|\']*[A-Za-z\_0-9\.\+]+["|\']*',comment) ## strings
+            strings=re.findall(r'[,&][A-Za-z\_\.0-9]+=["|\']*[A-Za-z\_0-9\.\+ ]+["|\']*',comment) ## strings
             treelist=re.findall(r'[,&][A-Za-z\_\.0-9]+={[A-Za-z\_,{}0-9\.]+}',comment) ## complete history logged robust counting (MCMC trees)
-            sets=re.findall(r'[,&][A-Za-z\_\.0-9\%]+={[A-Za-z\.\-0-9eE,\"\_]+}',comment) ## sets and ranges
+            sets=re.findall(r'[,&][A-Za-z\_\.0-9\%]+={[A-Za-z\.\-0-9 ,\"\_]+}',comment) ## sets and ranges
             figtree=re.findall(r'\![A-Za-z]+=[A-Za-z0-9#]+',comment) ## figtree comments, in case MCC was manipulated in FigTree
 
             for vals in strings: ## string states go here