# CELTX CHARACTER + SCENE INVOLVEMENT SCRIPT
# ######################################################################

'''

This program opens a .celtx file, and reads the script. It finds all of
the unique characters in the said script, then puts together a list of 
characters. It then compiles a list of all the scenes, and lists which 
characters speak in each scene.

Celtx does not reindex characters in the main catalogue, making it a 
poor tool to track characters. This script provides an alternate way
to track characters.

'''

# ######################################################################

from tkFileDialog import askopenfilename      
from Tkinter import Tk
from sys import exit
import zipfile

# ######################## LOAD CELTX FILE #############################

# Ask the user to select a .celtx file to open.
Tk().withdraw()
filename = askopenfilename(title='Choose a Celtx file', filetypes=[('Celtx File','*.celtx'), ('Any File','*.*')])

# If the user does not choose a file, quit.
if filename == "":
	exit("No file selected. Quitting")
	
# Unzip the file to a temporary directory.
celtxfile = zipfile.ZipFile(filename)
celtxfile.extractall("./temp_celtx/")
celtxfile.close()

# Print the file name for the user.
print ":: " + filename[filename.rfind("/")+1:filename.find(".celtx")].upper() + " CELTX FILE"
print ""

# ######################## READ PROJECT FILE ###########################

#  characterList.append(character name, description)
characterList = list()

# Open the project in the temporary directory
projectfile = open("./temp_celtx/project.rdf")
line = projectfile.readline()

# Read through the file line by line.
while line:
	
	if line.find("<cx:Cast ") > -1:
		description = ""
		name = ""
		while True:
			if line.find("dc:title=") > -1:
				name = line[line.find("dc:title=\"")+len("dc:title=\""):line.find("\"", line.find("dc:title=\"")+len("dc:title=\""))]
			if line.find("dc:description=") > -1:
				description = line[line.find("dc:description=\"")+len("dc:description=\""):line.find("\"", line.find("dc:description=\"")+len("dc:description=\""))]
			if line.find("</cx:Cast>") > -1 or line.find("/>") > -1:
				break
			line = projectfile.readline()
		characterList.append([name.upper(), description])
		
	# Grab the next line.
	line = projectfile.readline()
		
# Close the project file.
projectfile.close()

# ##########
# ##########
# ##########

# Print the list of characters.
print "COMPLETE LIST OF CHARACTERS (" + str(len(characterList)) + " Total)"
print "#####################################################"

for character in sorted(characterList):
	print "  " + character[0]
print ""

# Print the list of characters.
print "COMPLETE LIST OF CHARACTERS WITH DESCRIPTIONS"
print "#####################################################"

for character in sorted(characterList):
	print "  " + character[0] 
	if len(character[1].strip()) > 0:
		print "     " + character[1]
	print ""
print ""

# ######################### READ SCRIPT FILE ###########################

# Lists in memory
#  characterList.append(character name)
#  sceneList.append( ['scene number', 'scene name', ['character #1', 
#                                                      'character #2']])
characterList = list()
sceneList = list()

# Temporary Variables
currentSceneNumber = ""
currentSceneName = ""
currentSceneCharacterList = list()

# ##########
# ##########
# ##########

# Open the script in the temporary directory
scriptfile = open("./temp_celtx/script-HU6.html")
line = scriptfile.readline()

# Read through the file line by line.
while line:
	
	# New scene heading
	if line[0:len("<p scenestr=")] == "<p scenestr=":
		
		# Print the last heading, character list.
		if currentSceneName != "":
			sceneList.append([currentSceneNumber, currentSceneName, currentSceneCharacterList])
		
		# Grab the heading, could be multiline.
		currentSceneName = line[line.find(">")+1:line.find("<br>")].strip()
		currentSceneNumber = line[line.find("scenenumber=\"")+len("scenenumber=\""):line.find("\"", line.find("scenenumber=\"")+len("scenenumber=\""))]
		if line.find("<br>") < 0:
			line = scriptfile.readline()
			currentSceneName += " " + line[:line.find("<br>")].strip()
		currentSceneName = currentSceneName.upper().replace("  ", " ").replace("</P>", "").strip()
		
		# Clear the current character list.
		currentSceneCharacterList = list()
		
	# Add the character listed
	if line[0:len("<p class=\"character\">")] == "<p class=\"character\">":
		character = line[line.find("<p class=\"character\">")+len("<p class=\"character\">"):].upper()
		character = character.replace("<BR>", "").replace("</P>", "").replace("&AMP;", "&").strip()
		currentSceneCharacterList.append(character)
		characterList.append(character)
		
	# Grab the next line.
	line = scriptfile.readline()

# Do the final scene.	
sceneList.append([currentSceneNumber, currentSceneName, currentSceneCharacterList])
	
# Close the script file.
scriptfile.close()

# ##########
# ##########
# ##########

# Print the list out of characters.
print "CHARACTERS WITH LINES OF DIALOG (" + str(len(set(characterList))) + " Total)"
print "#####################################################"

for character in sorted(set(characterList)):
	print "  " + character
	
# Print the list out of scenes and characters involved.
print "\r\n\r\nSCENES / CHARACTERS w. DIALOG"
print "#####################################################"

for scene in sceneList:
	print "\r\n"
	print scene[0] + ": " + scene[1]
	for character in sorted(set(scene[2])):
		print "     - " + character