Merge pull request #202 from freelawproject/improve-reference-citations

Improve reference citations
freelawproject · Feb 7, 2025 · 6e7ec51 · 6e7ec51
2 parents 40619c7 + 9ca0665
commit 6e7ec51
Show file tree

Hide file tree

Showing 3 changed files with 109 additions and 0 deletions.
diff --git a/eyecite/find.py b/eyecite/find.py
@@ -29,6 +29,7 @@
 )
 from eyecite.regexes import SHORT_CITE_ANTECEDENT_REGEX, SUPRA_ANTECEDENT_REGEX
 from eyecite.tokenizers import Tokenizer, default_tokenizer
+from eyecite.utils import DISALLOWED_NAMES
 
 
 def get_citations(
@@ -153,6 +154,7 @@ def is_valid_name(name: str) -> bool:
             and name[0].isupper()
             and not name.endswith(".")
             and not name.isdigit()
+            and name.lower() not in DISALLOWED_NAMES
         )
 
     regexes = [

diff --git a/eyecite/utils.py b/eyecite/utils.py
@@ -4,6 +4,107 @@
 
 from lxml import etree
 
+# Names not allowed to be reference citations
+# this is partially taken from juriscraper
+DISALLOWED_NAMES = [
+    # Common options
+    "state",
+    "united states",
+    "people",
+    "commonwealth",
+    "mass",
+    "commissioner"
+    # AGs
+    "Akerman",
+    "Ashcroft",
+    "Barr",
+    "Bates",
+    "Bell",
+    "Berrien",
+    "Biddle",
+    "Black",
+    "Bonaparte",
+    "Bork",
+    "Bondi",
+    "Bradford",
+    "Breckinridge",
+    "Brewster",
+    "Brownell",
+    "Butler",
+    "Civiletti",
+    "Clark",
+    "Clement",
+    "Clifford",
+    "Crittenden",
+    "Cummings",
+    "Cushing",
+    "Daugherty",
+    "Devens",
+    "Evarts",
+    "Filip",
+    "Garland",
+    "Gerson",
+    "Gilpin",
+    "Gonzales",
+    "Gregory",
+    "Griggs",
+    "Grundy",
+    "Harmon",
+    "Hoar",
+    "Holder",
+    "Jackson",
+    "Johnson",
+    "Katzenbach",
+    "Keisler",
+    "Kennedy",
+    "Kleindienst",
+    "Knox",
+    "Lee",
+    "Legaré",
+    "Levi",
+    "Lincoln",
+    "Lynch",
+    "MacVeagh",
+    "Mason",
+    "McGranery",
+    "McGrath",
+    "McKenna",
+    "McReynolds",
+    "Meese",
+    "Miller",
+    "Mitchell",
+    "Moody",
+    "Mukasey",
+    "Murphy",
+    "Nelson",
+    "Olney",
+    "Palmer",
+    "Pierrepont",
+    "Pinkney",
+    "Randolph",
+    "Reno",
+    "Richardson",
+    "Rodney",
+    "Rogers",
+    "Rush",
+    "Sargent",
+    "Saxbe",
+    "Sessions",
+    "Smith",
+    "Speed",
+    "Stanbery",
+    "Stanton",
+    "Stone",
+    "Taft",
+    "Taney",
+    "Thornburgh",
+    "Toucey",
+    "Whitacker",
+    "Wickersham",
+    "Williams",
+    "Wirt",
+]
+
 
 def strip_punct(text: str) -> str:
     """Strips punctuation from a given string

diff --git a/tests/test_FindTest.py b/tests/test_FindTest.py
@@ -502,6 +502,12 @@ def test_find_citations(self):
                                       'defendant': 'Bar',
                                       'pin_cite': '347-348'}),
               reference_citation('Foo at 62', metadata={'plaintiff': 'Foo', 'pin_cite': '62'})]),
+            ('Foo v. United States 1 U.S. 12, 347-348. something something ... the United States at 1776 we see that and Foo at 62',
+             [case_citation(page='12',
+                            metadata={'plaintiff': 'Foo',
+                                      'defendant': 'United States',
+                                      'pin_cite': '347-348'}),
+              reference_citation('Foo at 62', metadata={'plaintiff': 'Foo', 'pin_cite': '62'})]),
             # Test that reference citation must occur after full case citation
             ('In Foo at 62 we see that, Foo v. Bar 1 U.S. 12, 347-348. something something,',
              [case_citation(page='12',