Update Parser.py

Parser.py

@@ -59,9 +59,8 @@ def get_splits(folderpath):
     full_body_text = "\n".join(body_texts).replace('-', '')
     full_body_text = correct(full_body_text, "justice")
 
-    # split_p = re.compile('((\n|^)\s*Per Curiam\.\s*\n)|((\n|^)\s*(Mr\.\s*(chief)?\s*)?Justice[A-z\s\n,]*delivered the opinion)|((\n|^)\s*(mr\.\s*)?justice[A-Za-z\n\s,–-]*(concurring|dissenting)[A-Za-z\n\s,–]*\.)', re.IGNORECASE)
     split_p = re.compile('((\n|^)\s*Per Curiam\.\s*\n)|(Justice[A-z\s\n,]*delivered the opinion)|((\n|^)\s*(mr\.\s*)?justice[A-Za-z\n\s,–-]*(concurring|dissenting)[A-Za-z\n\s,–]*\.)', re.IGNORECASE)
-
+    # ((\n|^)\s*(Mr\.\s*(chief)?\s*)?Justice[A-z\s\n,]*delivered the opinion)
     splits_m = list(re.finditer(split_p, full_body_text))
     splits = []
 
@@ -147,6 +146,20 @@ def correct(corpus, keyword):
                 words[ind] = result[0][0]
     return " ".join(words)
 
+def closest_justice(name, datetime):
+    cy = court_from_year(datetime)
+    justices = cy['Associate']
+    if cy['Chief'] is not None:
+        justices += [cy['Chief']]
+    if name.capitalize() not in justices:
+        scores = [distance(j, name) for (i,j) in enumerate(justices)]
+        closest_name = justices[np.argmin(scores)]
+        if closest_name.capitalize() == cy['Chief']:
+            closest_name = "Chief"
+        return closest_name
+    else:
+        return name
+
 class Opinion:
     def __init__(self, opinion_type, author, joining, body_text, fn_text, header_text):
         self.opinion_type = opinion_type
@@ -193,7 +206,11 @@ class Case:
     def update_majority_joining(self):
         print("Getting updated list")
         cy = court_from_year(self.date)
-        known = [j for d in self.dissents for j in d.joining] + [d.author for d in self.dissents] + [j for c in self.concurrences for j in c.joining] + [c.author for c in self.concurrences] + [self.majority.author] + [r for r in self.recused]
+        known = [j for d in self.dissents for j in d.joining] + [d.author for d in self.dissents] + [j for c in
+                                                                                                     self.concurrences
+                                                                                                     for j in
+                                                                                                     c.joining] + [
+                    c.author for c in self.concurrences] + [self.majority.author] + [r for r in self.recused]
         all_justices = [aj for aj in cy['Associate']]
         if cy['Chief'] is not None:
             all_justices.append('Chief')
@@ -254,8 +271,18 @@ class Case:
         if self.case_citation is not None and self.case_citation.lower().split('s.')[-1].strip() == "":
             self.case_citation = self.case_citation.strip() + ' ' + str(self.page_numbers[0])
 
+    def update_justice_names(self):
+        if self.majority.author.lower() != "per curiam":
+            self.majority.author = closest_justice(self.majority.author, self.date)
+        for (i,cons) in enumerate(self.concurrences):
+            self.concurrences[i].author = closest_justice(self.concurrences[i].author, self.date)
+        for (i,dissents) in enumerate(self.dissents):
+            self.dissents[i].author = closest_justice(self.dissents[i].author, self.date)
+        return
+
     def process(self):
         self.get_date()
+        self.update_justice_names()
         self.update_recused()
         self.update_majority_joining()
         self.get_cert_info()