Update Parser.py
Browse files
Parser.py
CHANGED
|
@@ -59,7 +59,9 @@ def get_splits(folderpath):
|
|
| 59 |
full_body_text = "\n".join(body_texts).replace('-', '')
|
| 60 |
full_body_text = correct(full_body_text, "justice")
|
| 61 |
|
|
|
|
| 62 |
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,β-]*(concurring|dissenting)[A-Za-z\n\s,β]*\.)', re.IGNORECASE)
|
|
|
|
| 63 |
splits_m = list(re.finditer(split_p, full_body_text))
|
| 64 |
splits = []
|
| 65 |
|
|
|
|
| 59 |
full_body_text = "\n".join(body_texts).replace('-', '')
|
| 60 |
full_body_text = correct(full_body_text, "justice")
|
| 61 |
|
| 62 |
+
# 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,β-]*(concurring|dissenting)[A-Za-z\n\s,β]*\.)', re.IGNORECASE)
|
| 63 |
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,β-]*(concurring|dissenting)[A-Za-z\n\s,β]*\.)', re.IGNORECASE)
|
| 64 |
+
|
| 65 |
splits_m = list(re.finditer(split_p, full_body_text))
|
| 66 |
splits = []
|
| 67 |
|