fix issue with multiple nulls in wos (#42)

odarbelaeze · web-flow · commit 3bbdda81b7a9 · 2025-03-15T12:42:21.000Z
* Allow null multiple times at the beginning of a line

* Update version
diff --git a/src/bibx/__init__.py b/src/bibx/__init__.py
@@ -28,7 +28,7 @@
     "read_wos",
 ]
 
-__version__ = "0.6.2"
+__version__ = "0.6.3"
 
 
 def query_openalex(
diff --git a/src/bibx/builders/wos.py b/src/bibx/builders/wos.py
@@ -61,7 +61,7 @@ class WosCollectionBuilder(CollectionBuilder):
     """Builder for collections of articles from Web of Science (WoS) ISI files."""
 
     ISI_LINE_PATTERN = re.compile(
-        r"^(null|.)?((?P<field>[A-Z0-9]{2})|  )( (?P<value>.*))?$"
+        r"^((null)+|.)?((?P<field>[A-Z0-9]{2})|  )( (?P<value>.*))?$"
     )
     ISI_CITATION_PATTERN = re.compile(
         r"""^(?P<AU>[^,]+),[ ]          # First author

Original file line number	Diff line number	Diff line change
`@@ -61,7 +61,7 @@ class WosCollectionBuilder(CollectionBuilder):`
`61`	`61`	`"""Builder for collections of articles from Web of Science (WoS) ISI files."""`
`62`	`62`
`63`	`63`	`ISI_LINE_PATTERN = re.compile(`
`64`		`- r"^(null\|.)?((?P<field>[A-Z0-9]{2})\| )( (?P<value>.*))?$"`
	`64`	`+ r"^((null)+\|.)?((?P<field>[A-Z0-9]{2})\| )( (?P<value>.*))?$"`
`65`	`65`	`)`
`66`	`66`	`ISI_CITATION_PATTERN = re.compile(`
`67`	`67`	`r"""^(?P<AU>[^,]+),[ ] # First author`