Yup

Analyser.py

@@ -1,28 +1,149 @@
 import json
 import sys, os
-Cast = {}
+import Analyser
+import re
 
-string = sys.argv[1]
-temp = ""
-arrayOfStrings = []
-space = " "
+
+
+### VARIABLES
+
+Cast = [] #an array of cast members
+string = "sys.argv[1]" #the location of the current file we want to convert
+temp = "" #temp string
+spaces = [] #an array of spaces we want to check since some of the formating is lost and newlines are replaced by a bunch of spaces
+spacesRev = []
+space = " " #a space var that is used to initiate the spaces list
+finishstring = "FINISHEDTHESTRINGS" #finished string meant to check for when we run a huge string through a while loop, when it's done splitting everything, the main string will change name to finishedstring
+
+
+### VAR INITIATERS
+
+
+## FILS THE SPACES LIST WITH AMOUNTS OF SPACES WE WILL WANT TO SPLIT FROM.
 for x in range(0, 100):
-    arrayOfStrings.append(space)
     space = space+" "
+    spaces.append(space)
 
+for i in reversed(spaces):
+    spacesRev.append(i)
 
+### FUNCTIONS
 
-with open(string, "r") as infile:
+##SPLITTER
+#takes two arguments, the string to split and the array to append the part it split. Checks for any amount of spaces longer then 1 space
+
+def splitter(string, array):
+    global spacesRev #get all spaces for comparison
+    global finishstring #get universally set finishstring
+    index = -1
+    lowestStart = -1
+    for space in spaces:
+        m = re.search(space, string)
+        if m is not None:
+            tempStart = m.start()
+            tempEnd =  m.end()
+        else:
+            index=-1
+            continue
+        if (tempEnd > index or index == -1) and (tempStart <= lowestStart or lowestStart == -1):
+            index = tempStart
+            lowestStart = tempEnd
+    if index > -1:
+        beforeSplit = string[:index]
+        afterSplit = string[lowestStart:]
+        array.append(beforeSplit)
+        return afterSplit
+    else:
+        array.append(string)
+        return finishstring
+
+def Folder(folder):
+    global Cast
+    for file in os.listdir(folder):
+        if file.endswith(".txt"):
+            filename = file[:3];
+            with open(folder+"/"+file, "r") as infile:
                 fileNaam=infile.read().replace('\n', '     ')
-    array=fileNaam.split()
-    arrayFromCast = array[array.index("CAST")+1:]
-    Cast=arrayFromCast[:arrayFromCast.index("STAR")];
-
-
-
-
-with open('output.json', 'w+') as outfile:
+                fileNaam = fileNaam.replace('\t', '     ')
+                x = 0
+                while fileNaam != finishstring:
+                    fileNaam = splitter(fileNaam, Cast)
+                    if(x < len(fileNaam)) and x is not 0:
+                        break
+                    x = len(fileNaam)
+                    print('only ' + str(x) + " characters left from file " + folder+"/"+file + ", rest is being written to Output/" + folder+"/"+file + '.json')
+            with open('Output/'+folder+"/"+file+'.json', 'w+') as outfile:
                json.dump(Cast, outfile)
-with open('Temp.txt', 'w+') as outfile:
-    outfile.write(temp)
-    outfile.close()
+            if "CAST" in Cast:
+                CheckCast = Cast.index("CAST")
+                tempAr =Cast[CheckCast:]
+                if "STAR TREK: THE NEXT GENERATION" in tempAr:
+                    endOfCast = tempAr.index("STAR TREK: THE NEXT GENERATION")
+                else:
+                    endOfCast = -1
+            else:
+                CheckCast = -1
+                endOfCast = -1
+
+            if (CheckCast is not -1) and (endOfCast is not -1):
+                print(CheckCast)
+                print(endOfCast)
+                with open('Output/'+file+'-Casts.json', 'w+') as outfile:
+                    temp = Cast[CheckCast+1:CheckCast+endOfCast]
+                    print(temp)
+                    json.dump(temp, outfile)
+            Cast = []
+
+def File(file):
+    global Cast
+    with open(file, "r") as infile:
+        fileNaam=infile.read().replace('\n', '     ')
+        fileNaam = fileNaam.replace('\t', '     ')
+        x = 0
+        while fileNaam != finishstring:
+            fileNaam = splitter(fileNaam, Cast)
+            if(x < len(fileNaam)) and x is not 0:
+                break
+            x = len(fileNaam)
+            print('only ' + str(x) + " characters left from file " + file + ", rest is being written to Output/" + file + '.json')
+    with open('Output/'+file+'.json', 'w+') as outfile:
+       json.dump(Cast, outfile)
+    if "CAST" in Cast:
+        CheckCast = Cast.index("CAST")
+        tempAr =Cast[CheckCast:]
+        if "STAR TREK: THE NEXT GENERATION" in tempAr:
+            endOfCast = tempAr.index("STAR TREK: THE NEXT GENERATION")
+        else:
+            endOfCast = -1
+    else:
+        CheckCast = -1
+        endOfCast = -1
+
+    if (CheckCast is not -1) and (endOfCast is not -1):
+        print(CheckCast)
+        print(endOfCast)
+        with open('Output/'+file+'-Casts.json', 'w+') as outfile:
+            temp = Cast[CheckCast+1:CheckCast+endOfCast]
+            print(temp)
+            json.dump(temp, outfile)
+    Cast = []
+
+
+def Main():
+    if len(sys.argv) > 1:
+        if (os.path.isdir(sys.argv[1])):
+            print("folder")
+            Folder(sys.argv[1])
+        if (os.path.isfile(sys.argv[1])):
+            print("file")
+            File(sys.argv[1])
+        else:
+            print("Invalid file")
+            input()
+    else:
+        print('no argument')
+        input()
+
+
+
+Main()

Output/103.txt-Casts.json

@@ -0,0 +1 @@
+["PICARD", "SARAH MACDOUGAL", "RIKER", "JIM SHIMODA", "DATA", "CREWMAN (2)", "TROI", "CREWWOMAN", "BEVERLY", "SECURITY GUARD", "TASHA", "TRANSPORTER CHIEF", "WORF", "CONN", "GEORDI", "WESLEY"]

Output/109.txt-Casts.json

@@ -0,0 +1 @@
+["PICARD", "FIRST EDO CITIZEN", "RIKER", "TWO EDO CITIZENS", "DATA", "RIVAN (YOUNG FEMALE EDO)", "TROI", "LIATOR (MALE EDO)", "BEVERLY", "EDOLORD", "TASHA", "FIRST EDO BOY", "GEORDI", "CONN CREWMEMBER", "WORF", "EDO GIRL", "WESLEY", "SECOND EDO BOY", "FIRST MEDIATOR (MALE EDO)", "SECOND MEDIATOR (MALE EDO)", "EDO", "ADULTS", "CHILDREN", "MUSIC GROUP OF EDO HARPISTS", "TRANSPORTER CHIEF", "MEDICAL TECHNICIAN", "STAR TREK: \"Justice\" - 9/4/87 - SETS"]

Output/110.txt-Casts.json

@@ -0,0 +1 @@
+["PICARD", "FERENGI:", "RIKER", "DAIMON BOK", "BEVERLY", "KAZAGO", "DATA", "RATA", "TROI", "TASHA", "STARGAZER:", "GEORDI", "PHANTOM BRIDGE CREW", "WORF", "VOICES (V.O.)", "WESLEY", "FIRST VOICE (V.O.)", "SECOND VOICE (V.O.)", "THIRD VOICE (V.O.)", "STAR TREK: \"The Battle\" - 9/14/87 - SETS"]

Output/111.txt-Casts.json

@@ -0,0 +1 @@
+["PICARD", "\"Q\"", "RIKER", "WOMAN (SURVIVOR)", "BEVERLY", "BEVERLY", "DATA", "Non-Speaking Roles", "TROI", "CREWMEMBERS", "TASHA", "SICKBAY STAFF", "GEORDI", "TWO SENTRIES", "WORF", "ANIMAL-SOLDIERS", "WESLEY", "DOZEN SURVIVORS", "CHILD (FEMALE SURVIVOR)", "STAR TREK: Hide And \"Q\" - 9/25/87 - SETS"]

Output/180.txt-Casts.json

@@ -0,0 +1 @@
+["PICARD", "HAYNE", "RIKER", "ISHARA YAR", "DATA", "COALITION MAN #1", "BEVERLY", "TAN TSU", "TROI", "GEORDI", "WORF", "Non-Speaking", "VARIOUS TURKANANS", "O'BRIEN", "COALITION MEMBERS", "ALLIANCE MEMBERS", "Non-Speaking", "SUPERNUMERARIES", "STAR TREK: \"Legacy\" - 8/20/90 - SETS"]

Output/181.txt-Casts.json

@@ -0,0 +1 @@
+["PICARD", "K'MPEC", "RIKER", "DURAS", "DATA", "GOWRON", "BEVERLY", "K'EHLEYR", "TROI", "ALEXANDER", "GEORDI", "KLINGON GUARD #1", "WORF", "KLINGON GUARD #2", "TRANSPORTER TECHNICIAN", "SECURITY OFFICER", "Non-Speaking", "Non-Speaking", "SECURITY GUARDS", "4 KLINGON RETAINERS", "2 CHILDREN", "NURSE", "MEDICAL TECHNICIAN", "SUPERNUMERARIES", "STAR TREK: \"Reunion\" - 9/4/90 - SETS"]

Output/199.txt-Casts.json

@@ -0,0 +1 @@
+["PICARD", "ENSIGN JENNA D'SORA", "RIKER", "DATA", "ENSIGN McKNIGHT", "BEVERLY", "TROI", "GEORDI", "WORF", "GUINAN", "O'BRIEN", "KEIKO", "COMPUTER VOICE", "Non-Speaking", "NURSE", "SECURITY OFFICERS", "THORNE", "LIEUTENANT VAN MAYTER", "DATA'S CAT", "SUPERNUMERARIES", "STAR TREK: \"In Theory\" - 3/20/91 - SETS"]

Output/274.txt-Casts.json

@@ -0,0 +1 @@
+["PICARD", "BOK", "RIKER", "JASON", "DATA", "BIRTA", "BEVERLY", "TOL", "TROI", "RHODES", "WORF", "COM VOICE", "GEORDI", "Non-Speaking", "Non-Speaking", "N.D. SUPERNUMERARIES", "N.D FERENGI", "STAR TREK: \"Bloodlines\" - 02/09/94 - SETS"]

Output/Data/Tng/103.txt-Casts.json

@@ -0,0 +1 @@
+[]

Output/Data/Tng/109.txt-Casts.json

@@ -0,0 +1 @@
+[]

Output/Data/Tng/110.txt-Casts.json

@@ -0,0 +1 @@
+[]

Output/Data/Tng/111.txt-Casts.json

@@ -0,0 +1 @@
+[]

Output/Data/Tng/148.txt-Casts.json

@@ -0,0 +1 @@
+[]

Output/Data/Tng/180.txt-Casts.json

@@ -0,0 +1 @@
+[]