Update parse_info.py

parse_info.py

@@ -1,11 +1,4 @@
-import string
-import chardet, string, gdown, re
-from pathlib import Path
-from nltk import everygrams
-from collections import Counter
-from typing import List, Optional
-from datetime import datetime
-from dateutil import parser, relativedelta
+from imports import *
 
 punc = list(string.punctuation)
 def parse_string(inp: str, rep=" ", punc=punc, excp=[]) -> str:
@@ -90,4 +83,27 @@ def parse_designation(inp: List) -> str:
 
 def parse_email(inp: List) -> str:
     inp = list(set([parse_string(i, rep="", excp=["@","."]) for i in inp]))
-    return " ".join(inp)
+    return " ".join(inp)
+
+def decontracted(phrase) -> str:
+    phrase = re.sub(r"â€|™|“|”|;|ü|\xad|\xa0|\u200b|·|∙|�|●|�|§|•|!|▪|©|\?|\]|\[|\)|\(", "", phrase)
+    phrase = phrase.strip()
+    phrase = unicodedata.normalize("NFC", phrase)
+    if "   " in phrase or "  " in phrase: # check space character 
+        phrase = phrase.replace("   ","_").replace("  ","_").replace(" ","").replace("_"," ")
+    tmp = phrase.split(" ")
+    check_parse = True
+    for i in tmp:
+        if len(i) > 1:
+            check_parse = False
+            break
+    if check_parse:
+        phrase = phrase.replace(" ","")
+    # phrase = phrase.replace("   "," ").replace("  "," ")
+    return phrase.replace("\n"," ")
+
+def normalize_bbox(bbox, size): # must normalize bbox to [0;1000]
+    return [int(1000 * bbox[0] / size[0]),
+            int(1000 * bbox[1] / size[1]),
+            int(1000 * bbox[2] / size[0]),
+            int(1000 * bbox[3] / size[1])]