Update postt.py

postt.py

@@ -42,4 +42,25 @@ def postcor(blist):
     for rw in remrow:
         crlist.remove(rw)
     
-    return crlist
+    return crlist
+ 
+ 
+def precor(text):
+    lines = text
+    lines = lines.replace("breast and prostate cancer","breast cancer and prostate cancer")
+    lines = lines.replace("prostate and breast cancer","prostate cancer and breast cancer")
+    lines = lines.replace("breast, prostate and ovarian cancer","breast cancer, prostate cancer and ovarian cancer")
+    lines = re.sub(r"\[\d*\]", "", lines)  # notes
+    lines = re.sub(r'\(\s?(figure|Figure|table|Table|fig\.|Fig\.|tab\.|Tab\.)(\s?\w)*\s?\)',"", lines)  # (figure)|(table)
+    lines = re.sub(r'www\.(?:[-\w.]|(?:%[\da-fA-F]{2}))+', "", lines)  # www.ex.com
+    lines = re.sub(r'https?://(?:[-\w.]|(?:%[\da-fA-F]{2}))+', "", lines)  # http urls
+    lines = re.sub(r'[a-zA-Z0-9]+[_\-.]*[a-zA-Z0-9]*@[a-zA-Z0-9]+\.\w+', "", lines)  # emails
+    lines = re.sub(r'\(\)', "", lines)
+    lines = re.sub(r'\[\s?[0-9]+(\–|,|\-)\s?[0-9]+\s?\]', "", lines)
+    lines = re.sub(r'\(\s?[0-9]+(\–|,|\-)\s?[0-9]+\s?\)', "", lines)
+    lines = re.sub(r'\[\s?[0-9]+(\–|,|\-)?\s?[0-9]*\s?\]', "", lines)
+    lines = re.sub(r'\(\s?[0-9]+(\–|,|\-)?\s?[0-9]*\s?\)', "", lines)
+    punc = ";.,?([)]"
+    for e in punc:
+        lines = lines.replace(e, " "+e+" ")
+    return lines