Editorial Workflows

#coding: utf-8
import workflow
import fnmatch
import os
import editor

def get_words(filename, ignore_case=True):
	with open(filename) as fp:
		for line in fp:
			for word in line.split():
				if ignore_case:
					word = word.lower()
				yield word
                
def get_parameters(action_in):
	inputs = action_in.split('\n') +['']*5
	wordlist, path, include_pattern, exclude_pattern, ignore_case = [i.strip() for i in inputs[:5]]
	if ignore_case == '':
		ignore_case = True
	else:
		if ignore_case == 'ON':
			ignore_case = True
		else:
			ignore_case = False
	if path:
		if path == '.':			
			path = os.path.split(editor.get_path())[0]
		elif not path.startswith('/'):
			path = os.path.join(os.path.expanduser('~/Documents'), path)		
	else:
		path = os.path.expanduser('~/Documents')
	return (wordlist, path, include_pattern, exclude_pattern, ignore_case)

def search_files(wordlist, directory, ignore_case=True,
		include_pattern=None, exclude_pattern=None):
	if ignore_case:
		wordset = set([w.lower() for w in wordlist.split()])
	else:
		wordset = set(wordlist.split())
	fnlist = []
	for dirpath, dirs, files in os.walk(directory):
		for filename in files:
			fname = os.path.join(dirpath, filename)
			to_include = True
			if exclude_pattern:
				if fnmatch.fnmatch(filename, exclude_pattern):
					to_include = False
			if include_pattern and to_include:
				if not fnmatch.fnmatch(filename, include_pattern):
					to_include = False
			if to_include:
				if wordset.issubset(get_words(fname, ignore_case)):
					fnlist.append(fname.split('Documents/')[1])
	return fnlist



action_in = workflow.get_input()
wordlist, path, include_pattern, exclude_pattern, ignore_case = get_parameters(action_in)
#print(wordlist, path, include_pattern, exclude_pattern, ignore_case)

action_out = '\n'.join(search_files(wordlist, path, 
											ignore_case=ignore_case,
											include_pattern=include_pattern,
											exclude_pattern=exclude_pattern))
print(action_out)
workflow.set_output(action_out)