Update terms and allow deleting terms

traiter/pylib/pipes/add.py

@@ -22,9 +22,13 @@ def term_pipe(
     name: str,
     path: Path | list[Path],
     default_labels: dict[str, str] | None = None,
+    delete_patterns: list[str] | str | None = None,
 ):
     default_labels = default_labels if default_labels else {}
     paths = path if isinstance(path, Iterable) else [path]
+    if isinstance(delete_patterns, str):
+        delete_patterns = delete_patterns.split()
+    delete_patterns = delete_patterns if delete_patterns else []
 
     # Gather terms and make sure they have the needed fields
     by_attr = defaultdict(list)
@@ -33,6 +37,8 @@ def term_pipe(
     for path in paths:
         terms = term_util.read_terms(path)
         for term in terms:
+            if term["pattern"] in delete_patterns:
+                continue
             label = term.get("label", default_labels.get(path.stem))
             pattern = {"label": label, "pattern": term["pattern"]}
             attr = term.get("attr", "lower").upper()

traiter/pylib/rules/terms/name_terms.csv

@@ -188,8 +188,10 @@ not_name,landing,lower,
 not_name,lat,lower,
 not_name,latitude,lower,
 not_name,legal,lower,
-not_name,liberty,lower,
+not_name,legal,lower,
+not_name,loam,lower,
 not_name,life,lower,
+not_name,limestone,lower,
 not_name,line,lower,
 not_name,list,lower,
 not_name,lng,lower,
@@ -258,6 +260,7 @@ not_name,puente,lower,
 not_name,puerto rico,lower,
 not_name,quad,lower,
 not_name,quadrangle,lower,
+not_name,quarter,lower,
 not_name,quartermaster,lower,
 not_name,railroad,lower,
 not_name,railway,lower,
@@ -282,6 +285,7 @@ not_name,rt,lower,
 not_name,rte,lower,
 not_name,s. paulo,lower,
 not_name,sampled,lower,
+not_name,san benito,lower,
 not_name,san diego,lower,
 not_name,san juan,lower,
 not_name,sci.,lower,
@@ -338,18 +342,21 @@ not_name_prefix,project,lower,
 not_name_prefix,project.,lower,
 not_name_prefix,sponsored by,lower,
 not_name_prefix,sponsored,lower,
+not_name_prefix,san,lower,
 not_name_prefix,state,lower,
 not_name_prefix,states,lower,
 not_name_prefix,station,lower,
 not_name_prefix,the university of,lower,
 not_name_prefix,the university,lower,
 not_name_prefix,univ. of,lower,
 not_name_prefix,university of,lower,
+not_name_prefix,upper,lower,
 not_name_suffix,area,lower,
 not_name_suffix,barcode,lower,
 not_name_suffix,biological,lower,
 not_name_suffix,co,lower,
 not_name_suffix,co.,lower,
+not_name_suffix,coastal,lower,
 not_name_suffix,collection,lower,
 not_name_suffix,community,lower,
 not_name_suffix,conservancy,lower,

traiter/pylib/rules/terms/unit_length_terms.csv

@@ -3,7 +3,7 @@ imperial_length,feet,ft,30.48
 imperial_length,foot,ft,30.48
 imperial_length,ft,ft,30.48
 imperial_length,ft.,ft,30.48
-imperial_length,in .,in,2.54
+imperial_length,in,in,2.54
 imperial_length,in.,in,2.54
 imperial_length,inch,in,2.54
 imperial_length,inches,in,2.54

traiter/pylib/term_util.py

@@ -40,6 +40,11 @@ def get_labels(
     return sorted(labels)
 
 
+def delete_terms(terms: list, patterns: list[str] | str) -> list:
+    patterns = patterns if isinstance(patterns, list) else patterns.split()
+    terms = [t for t in terms if t["pattern"] not in patterns]
+
+
 def labels_to_remove(
     csv_paths: Path | Iterable[Path],
     *,