Strip filename descriptions before checking

When checking for uncommon file extensions in the filename field
we should strip descriptions that are meant for SAF Bundler, for
example: Annual_Report_2020.pdf__description:Report. This ends up
as a false positive that spams the output with warnings.

CHANGELOG.md

@@ -12,7 +12,11 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - Use SPDX license data from SPDX themselves instead of spdx-license-list
 because it is deprecated and outdated
 - Require Python 3.9+
-- Don't run `fix.separators()` on title fields
+- Don't run `fix.separators()` on title or abstract fields
+- Don't run whitespace or newline fixes on abstract fields
+- Ignore some common non-SPDX licenses
+- Ignore `__description` suffix in filenames meant for SAFBuilder when checking
+for uncommon file extensions
 
 ### Updated
 - Python dependencies

csv_metadata_quality/app.py

@@ -90,11 +90,13 @@ def run(argv):
 
             continue
 
+        if args.unsafe_fixes:
+            match = re.match(r"^.*?abstract.*$", column)
+            if match is None:
                 # Fix: whitespace
                 df[column] = df[column].apply(fix.whitespace, field_name=column)
 
                 # Fix: newlines
-        if args.unsafe_fixes:
                 df[column] = df[column].apply(fix.newlines, field_name=column)
 
         # Fix: missing space after comma. Only run on author and citation
@@ -122,9 +124,9 @@ def run(argv):
         df[column] = df[column].apply(fix.unnecessary_unicode)
 
         # Fix: invalid and unnecessary multi-value separators. Skip the title
-        # field because sometimes "|" is used to indicate something like a
-        # subtitle.
-        match = re.match(r"^.*?title.*$", column)
+        # and abstract fields because "|" is used to indicate something like
+        # a subtitle.
+        match = re.match(r"^.*?(abstract|title).*$", column)
         if match is None:
             df[column] = df[column].apply(fix.separators, field_name=column)
             # Run whitespace fix again after fixing invalid separators

csv_metadata_quality/check.py

@@ -286,6 +286,11 @@ def filename_extension(field):
 
     # Iterate over all values
     for value in values:
+        # Strip filename descriptions that are meant for SAF Bundler, for
+        # example: Annual_Report_2020.pdf__description:Report
+        if "__description" in value:
+            value = value.split("__")[0]
+
         # Assume filename extension does not match
         filename_extension_match = False
 
@@ -312,8 +317,19 @@ def spdx_license_identifier(field):
     Prints the value if it is invalid.
     """
 
+    # List of common non-SPDX licenses to ignore
+    # See: https://ilri.github.io/cgspace-submission-guidelines/dcterms-license/dcterms-license.txt
+    ignore_licenses = {
+        "All rights reserved; no re-use allowed",
+        "All rights reserved; self-archive copy only",
+        "Copyrighted; Non-commercial educational use only",
+        "Copyrighted; Non-commercial use only",
+        "Copyrighted; all rights reserved",
+        "Other",
+    }
+
     # Skip fields with missing values
-    if pd.isna(field):
+    if pd.isna(field) or field in ignore_licenses:
         return
 
     spdx_licenses = load_spdx_licenses()

data/abstract-check.csv

@@ -0,0 +1,17 @@
+id,dc.title,dcterms.abstract
+1,Normal item,This is an abstract
+2,Leading whitespace, This is an abstract
+3,Trailing whitespace,This is an abstract 
+4,Consecutive whitespace,This is  an abstract
+5,Newline,"This
+is an abstract"
+6,Newline with leading whitespace," This
+ is an abstract"
+7,Newline with trailing whitespace,"This 
+is an abstract "
+8,Newline with consecutive whitespace,"This
+is an  abstract"
+9,Multiple newlines,"This
+is
+an
+abstract"