Handle citation strings

Closes #61

CHANGES.md

@@ -6,10 +6,12 @@
 
 ## Current Version
 
-- 0.10.10 (2022-11-08): Various improvements to courts-db
+- 0.10.11 (2022-11-17): Handle citation strings ([#61](https://github.com/freelawproject/courts-db/issues/61))
 
 ## Past Versions
 
+- 0.10.10 (2022-11-08): Various improvements to courts-db
+
 - 0.10.9 (2022-10-14): Updates to courts-db
 
 - 0.10.8 (2022-09-08): Add variation indiana tax court to match cl

courts_db/data/courts.json

@@ -26846,7 +26846,7 @@
     },
     {
         "case_types": [],
-        "citation_string": "E.D.N.Y",
+        "citation_string": "E.D.N.Y.",
         "court_url": "http://www.nyed.uscourts.gov/",
         "dates": [
             {
@@ -26860,6 +26860,7 @@
             }
         ],
         "examples": [
+            "E.D.N.Y.",
             "United States District Court E D New York",
             "United States District Court Eastern of New York",
             "District Court E D New York",
@@ -48189,6 +48190,7 @@
             }
         ],
         "examples": [
+            "W.D. Wash.",
             "United States District Court Western Distict of Washington At Seattle",
             "United States District Court For The Western Division of Washington",
             "United States District Court Westhern District"

courts_db/utils.py

@@ -197,5 +197,23 @@ def gather_regexes(courts):
                     court.get("location"),
                 )
             )
+        # Add a regex for the court's citation string, e.g. "W.D. Wash."
+        # See #61: https://github.com/freelawproject/courts-db/issues/61
+        regexes.append((
+            citation_to_regex(court["citation_string"]),
+            court["id"],
+            court["name"],
+            court["type"],
+            court.get("location"),
+        ))
 
     return regexes
+
+def citation_to_regex(citation_str: str):
+    reg_elements = citation_str.split(".")
+    reg_str = ""
+    for element in reg_elements:
+        if element != "":
+            reg_str += element.strip() + "\.\s?"
+    regex = re.compile(reg_str, (re.I | re.U))
+    return regex

setup.py

@@ -3,7 +3,7 @@
 
 from setuptools import find_packages, setup
 
-VERSION = "0.10.10"
+VERSION = "0.10.11"
 AUTHOR = "Free Law Project"
 EMAIL = "[email protected]"
 HERE = os.path.abspath(os.path.dirname(__file__))