Added GUI and fixed installer to work with it. Cleaned up some bugs when data output had one row only. Added float parsing. Updated string parsing to handle what looks like integers (0124).

Author: majora2007

README.md

@@ -15,5 +15,7 @@ https://raw.githubusercontent.com/first20hours/google-10000-english/master/googl
 N.B. This code is pretty messy, I wrote this in 2 hours. Don't judge. 
 
 Build:
-pyinstaller --onefile --add-data "templates/*.*;./templates" --add-data "words.txt;." easyjava.py
+//pyinstaller --onefile --add-data "templates/*.*;./templates" --add-data "words.txt;." easyjava.py
+Use:
+pyinstaller easyjava.spec
 

easyjava.py

@@ -5,6 +5,7 @@
 """
 import re
 import os
+
 from gooey import Gooey, GooeyParser
 
 import parse as parse
@@ -18,16 +19,19 @@ def get_argument(argument, default="None"):
 		return default
 
 def init_args():
-    parser = GooeyParser()
+
+    parser = GooeyParser(description='Enter the name of the POJO in Entity and select a file with pipe separated (|) values with included headers. Click typescript for typescript generation.')
     # Required Parameters
-    parser.add_argument('--entity', required=True, nargs=1, help="Name of the Entity")
-    parser.add_argument('--data', required=True, nargs=1, help="Pipe separated values (.txt) as result of query", widget='FileChooser')
+    parser.add_argument('--entity', required=True, nargs=1, metavar='Entity Name', help='Name of the Entity')
+    parser.add_argument('--data', required=True, nargs=1, metavar='Data', help='Pipe separated values as result of query', widget='FileChooser')
 
     # Optional
-    parser.add_argument('--typescript', required=False, action='store_true', help="If supplied, will output a typescript file as well for Entity")
+    parser.add_argument('--typescript', required=False, metavar='Typescript', action='store_true', help="Generate typescript")
 
     return parser.parse_args()
 
+
+
 def parse_data(data_file):
     types = []
     lines = []
@@ -39,8 +43,8 @@ def parse_data(data_file):
     print(header)
 
     line_data = []
-    for idx, cell in enumerate(lines):
-        line_data = [c for c in lines[idx].split('|') if c != '' and c != ' ']
+    for line in lines[1:]:
+        line_data = [c for c in line.split('|') if c != '' and c != ' ']
         if len(line_data) is len(lines[0]):
             break
 

easyjava.spec

@@ -10,17 +10,24 @@
 
 STRING_REGEXS = [
     # (E)thernet to the cell site - (P)lanning and (D)esign (D)atabase
-    re.compile(r'(?P<Type>[^\|\d])', re.IGNORECASE),
+    re.compile(r'(?P<Type>[^\|\d\.])', re.IGNORECASE),
     # ma0585
     re.compile(r'(?P<Type>[a-z]+[0-9]+)', re.IGNORECASE),
     # 05/01/2020
     re.compile(r'(?P<Type>\d{2}\/\d{2}\/\d{4})', re.IGNORECASE),
+    # 0123
+    re.compile(r'(?P<Type>0\d+)', re.IGNORECASE),
+]
+
+FLOAT_REGEXS = [
+    re.compile(r'(?P<Type>\d+\.\d*)', re.IGNORECASE)
 ]
 
 TYPE_REGEXS = {
     'String': STRING_REGEXS,
-    'int': INTEGER_REGEXS,
     'boolean': BOOLEAN_REGEXS,
+    'float': FLOAT_REGEXS,
+    'int': INTEGER_REGEXS,
 }
 
 

parse.py

@@ -32,9 +32,9 @@ def words(text): return re.findall('[a-z]+', text.lower())
 dictionary = Counter(words(open(words_path).read()))
 max_word_length = max(map(len, dictionary))
 total = float(sum(dictionary.values()))
-print('Loading words.txt from {0}'.format(words_path))
 
-print('total: {0}'.format(total))
+print('Loading words.txt from {0}'.format(words_path))
+print('Using word bank of: {0}'.format(total))
 
 def viterbi_segment(text):
     probs, lasts = [1.0], [0]