emaildump.py 16.1 KB
Newer Older
Cage, Marshall Andrew's avatar
Cage, Marshall Andrew committed
1
2
3
4
5
6
7
8
9
10
from arc.arcpreferences import PreferenceManager as PM
from arctool import ARCTool
from Default.emailfilter import EmailFilterTable, EmailFilterLogicValidator
from PyQt5.QtCore import QUrl, Qt
from PyQt5.QtGui import *
from PyQt5.QtWidgets import *
import arc.arcclasses as arcclasses
import arc.arcgui as arcgui
import quopri
import re
11
12
import imaplib
import email
Cage, Marshall Andrew's avatar
Cage, Marshall Andrew committed
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37

class Plugin(arcclasses.Plugin):
	headers = '|'.join(
		['From','Date','Sent','To','Cc','Bcc','Subject','Importance']
	)

	def __init__(self,package):
		super(Plugin,self).__init__(None,package)

		self.__name__ = "emaildump"
		# Required
		self.name = "Email Dump"
		self.authors = ["unonu"]
		self.version = (0,0,1)
		self.description="Finds a group of emails and dumps their information."
		self.contexts = ['Date']

		self.emails = []
		self.emailIds = {}
		self.fragments = {}
		self.fetched = False

		self.contextFilters = []

		self.igHeader = False
38
		self.igPles = False
Cage, Marshall Andrew's avatar
Cage, Marshall Andrew committed
39
40
41
42
43
44
45
46
47
48
49
50
51
52
		self.igReplies= False
		self.igDup 	  = False
		self.igFirstDup = False
		self.igImages = False
		self.igFormat = False
		self.igSpace = False

		self.delim = ''

	#needed
	def setupUi(self):
		#Filter
		self.widget.emailFilterTable = EmailFilterTable()
		self.widget.emailFilterTable.tableChanged.connect(
53
54
55
56
			lambda x: self.widget.fetchButton.setProperty('enabled',
				(x > 0
				or self.widget.contextCheck.isChecked()
				or self.widget.selectEdit.text() != ''))
Cage, Marshall Andrew's avatar
Cage, Marshall Andrew committed
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
		)
		self.widget.emailFilterTable.tableChanged.connect(
				ARCTool.signalProfileChanged
		)

		self.widget.tableLayout.addWidget(self.widget.emailFilterTable)
		self.widget.fetchButton.clicked.connect(self.makeRequest)
		self.widget.logicBox.setValidator(EmailFilterLogicValidator())
		self.widget.selectEdit.textChanged.connect(
			lambda x: self.widget.fetchButton.setEnabled(
				x != '' or len(self.widget.emailFilterTable) > 0
			)
		)

		#Options
		self.widget.contextCheck.stateChanged.connect(
			lambda x : self.widget.fetchButton.setEnabled(x > 0)
		)
		self.widget.headerCheck.stateChanged.connect(
			lambda x: self.setIgHeader(x > 0)
		)
78
79
80
		self.widget.plesCheck.stateChanged.connect(
			lambda x: self.setIgPles(x > 0)
		)
Cage, Marshall Andrew's avatar
Cage, Marshall Andrew committed
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
		self.widget.quoteCheck.stateChanged.connect(
			lambda x: self.setIgReplies(x > 0)
		)
		self.widget.dupCheck.stateChanged.connect(
			lambda x: self.setIgDup(x > 0)
		)
		self.widget.firstCheck.stateChanged.connect(
			lambda x: self.setIgFirstDup(x > 0)
		)
		self.widget.imageCheck.stateChanged.connect(
			lambda x: self.setIgImages(x > 0)
		)
		self.widget.formatCheck.stateChanged.connect(
			lambda x: self.setIgFormat(x > 0)
		)
		self.widget.spaceCheck.stateChanged.connect(
			lambda x: self.setIgSpace(x > 0)
		)
		self.widget.delimeterEdit.textChanged.connect(
			lambda: self.updateDelim()
		)
		self.widget.dupCheck.stateChanged.connect(
			lambda x: self.widget.dupWidget.setEnabled(x > 0)
		)
		self.widget.dupStrength.valueChanged.connect(
			lambda x: self.widget.dupLabel.setText('%d Words' %(x))
		)

	#call super
	def update(self):
		super(Plugin,self).update()

		#updated from extras
		if 'filters' in self.extras:
			self.widget.emailFilterTable.fromSerial(self.extras['filters'])

	#needed
	def storeOptions(self):
		self.options['logicBox'] =\
			(self.widget.logicBox.text(),'text')
		self.options['selectEdit'] =\
122
			(self.widget.selectEdit.text(),'text')
Cage, Marshall Andrew's avatar
Cage, Marshall Andrew committed
123
124
125
126
127
128
		self.options['delimeterEdit'] =\
			(self.widget.delimeterEdit.text(), 'text')
		self.options['contextCheck'] =\
			(self.widget.contextCheck.isChecked(), 'checked')
		self.options['headerCheck'] =\
			(self.widget.headerCheck.isChecked(), 'checked')
129
130
		self.options['plesCheck'] =\
			(self.widget.plesCheck.isChecked(), 'checked')
Cage, Marshall Andrew's avatar
Cage, Marshall Andrew committed
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
		self.options['quoteCheck'] =\
			(self.widget.quoteCheck.isChecked(), 'checked')
		self.options['dupCheck'] =\
			(self.widget.dupCheck.isChecked(), 'checked')
		self.options['firstCheck'] =\
			(self.widget.dupCheck.isChecked(), 'checked')
		self.options['imageCheck'] =\
			(self.widget.imageCheck.isChecked(), 'checked')
		self.options['formatCheck'] =\
			(self.widget.formatCheck.isChecked(), 'checked')
		self.options['spaceCheck'] =\
			(self.widget.spaceCheck.isChecked(), 'checked')
		self.options['dupStrength'] =\
			(self.widget.dupStrength.value(), 'value')

		self.extras['filters'] = self.widget.emailFilterTable.serialize()

	#override
	def generate(self):
		if not self.fetched:
			r = self.makeRequest()
			if r < 0:
				return None

		doc = QTextDocument()
		cursor = QTextCursor(doc)

		_c = _b = None
		for message in self.emails:
			_c = cursor.charFormat()
			_b = cursor.blockFormat()
			text = ''
			for part in message.walk():
				typ = part.get_content_type()
				dis = part.get('Content-Disposition')
				if dis != 'attachment':
					if typ == 'text/plain':
						try:
							text = ('<p>'
170
171
172
								+ re.sub(r'(?<=\r)\n',r'<br/>',
								part.get_payload(decode=True).decode('utf-8'))
								+ '</p>'
Cage, Marshall Andrew's avatar
Cage, Marshall Andrew committed
173
174
175
176
177
178
							)
						except UnicodeDecodeError:
							print("Couldn't decode this part")
							continue
					elif typ == 'text/html':
						try:
179
							text = part.get_payload(decode=True) \
Cage, Marshall Andrew's avatar
Cage, Marshall Andrew committed
180
181
182
183
								.decode('utf-8')
						except UnicodeDecodeError:
							print("Couldn't decode this part")
							continue
184
					elif 'image/' in typ and self.igImages is not True:
Cage, Marshall Andrew's avatar
Cage, Marshall Andrew committed
185
186
187
188
189
190
191
192
193
194
195
196
197
						# Embed image
						# print('embed image')
						dis = dis.split(';',1)
						# print(part.get('Content-ID'))
						# print(dis[1])
						if dis[0] == 'inline':
							img = QImage()
							img.loadFromData(part.get_payload(decode=True))
							doc.addResource(
								doc.ImageResource,
								QUrl('cid:'+part.get('Content-ID')[1:-1]),
								img
							)
198
			print('message converted')
Cage, Marshall Andrew's avatar
Cage, Marshall Andrew committed
199
200
			if self.igReplies:
				text = self.stripReplies(message,text)
201
202
203
			# if self.igPles:
			# 	text = self.stripPleasantries(text)
			print('replies ignored')
Cage, Marshall Andrew's avatar
Cage, Marshall Andrew committed
204
205
			if self.igHeader:
				text = self.stripHeaders(message,text)
206
			print('header ignored')
Cage, Marshall Andrew's avatar
Cage, Marshall Andrew committed
207
208
			cursor.insertHtml(text)
			if self.delim != '':
209
210
				cursor.insertHtml('<br/><p>' + chr(2) + '</p><br/>')
			print('message inserted')
Cage, Marshall Andrew's avatar
Cage, Marshall Andrew committed
211
212
213
214
215
216
217
218
219
220
			cursor.insertBlock()
			cursor.setCharFormat(_c)
			cursor.setBlockFormat(_b)

		if self.igFormat:
			cursor.select(cursor.Document)
			cursor.setCharFormat(_c)
			cursor.setBlockFormat(_b)
		if self.igImages:
			doc.setHtml(self.stripImages(doc.toHtml()))
221
			print('images stripped')
Cage, Marshall Andrew's avatar
Cage, Marshall Andrew committed
222
223
		if self.igDup:
			doc.setHtml(self.stripDuplicate(doc.toHtml()))
224
225
			print('duplicates stripped')
		doc.setHtml(doc.toHtml().replace(chr(2),self.delim))
Cage, Marshall Andrew's avatar
Cage, Marshall Andrew committed
226
227
		if self.igSpace:
			doc.setHtml(self.collapseSpace(doc.toHtml()))
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
			print('whitespace stripped')

		if self.igPles:
			plc = QTextCursor(doc)
			print('a')
			print(plc.position(), doc.characterCount())
			while plc.position() < doc.characterCount():
				print('b', plc.position())
				plc.movePosition(plc.EndOfBlock,plc.KeepAnchor)
				text = plc.selectedText()
				words = re.split(r'\b',text)
				if len(words) < 4:
					print(text)
					plc.removeSelectedText()
				plc.movePosition(plc.StartOfBlock)
			print('pleasantries forgone')
Cage, Marshall Andrew's avatar
Cage, Marshall Andrew committed
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264

		# print("generated")
		return doc

	def makeRequest(self):
		# make async? or at least talk to the user

		# Logic
		req, r, i = self.widget.emailFilterTable.getRequest(
			self.widget.logicBox.text()
		)

		if not req and r == 2:
			ARCTool.getStatusBar().showMessage(
				"Couldn't find filter label '%s'" %(i)
			)
			self.widget.logicBox.setSelection(
				self.widget.logicBox.text().find(i),len(i)
			)
			return -1

265
266
267
		if req == '':
			req = 'ALL'

Cage, Marshall Andrew's avatar
Cage, Marshall Andrew committed
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
		# Context
		if self.widget.contextCheck.isChecked():
			b = ARCTool.getContext().getBegin("d-MMM-yyyy")
			e = ARCTool.getContext().getEnd()
			if b:
				req += ' SINCE %s' %(b)
			if e:
				e = e.addDays(1)
				e = e.toString("d-MMM-yyyy")
				req += ' BEFORE %s' %(e)


		protocol = imaplib.IMAP4_SSL if PM.getPreference('Default Package',
														 'emailssl')\
									 else imaplib.IMAP4

		with protocol(
			PM.getPreference('Default Package','emailserver'),
286
			int(PM.getPreference('Default Package','emailport') or 993)
Cage, Marshall Andrew's avatar
Cage, Marshall Andrew committed
287
288
289
290
291
		) as M:
		
			passDialog = arcgui.LoginDialog(self.widget)
			try:
				passDialog.credentials.connect(
292
					lambda x, y: M.login(x,y) if not(x==y=='') else print('')
Cage, Marshall Andrew's avatar
Cage, Marshall Andrew committed
293
				)
294
				passDialog.exec()
Cage, Marshall Andrew's avatar
Cage, Marshall Andrew committed
295
296
297
298
299
300
301
302
			except:
				ARCTool.getStatusBar().showMessage(
					"Couldn't login to IMAP server."
				)
				return -1

			try:
				ARCTool.getStatusBar().showMessage(
303
					"Selecting mailbox..."
Cage, Marshall Andrew's avatar
Cage, Marshall Andrew committed
304
305
				)
				mailbox = self.widget.selectEdit.text()
306
				mailbox = re.sub(r'(["])',r'\\\g<0>',mailbox)
307
308
				if ((mailbox == '' or mailbox.lower() =='inbox')
					and req == 'ALL'):
Cage, Marshall Andrew's avatar
Cage, Marshall Andrew committed
309
					ARCTool.getStatusBar().showMessage(
310
311
						"Can't select Inbox without at least one filter.",
						5000
Cage, Marshall Andrew's avatar
Cage, Marshall Andrew committed
312
313
					)
					return -1
314
315
				M.select('"'+mailbox+'"' if mailbox != '' else 'INBOX',
					readonly=True)
Cage, Marshall Andrew's avatar
Cage, Marshall Andrew committed
316
317
				try:
					ARCTool.getStatusBar().showMessage(
318
319
320
						"Searching %s..." %(
							mailbox if mailbox != '' else 'Inbox'
						)
Cage, Marshall Andrew's avatar
Cage, Marshall Andrew committed
321
322
323
324
					)
					typ, data = M.search(None, req)
				except protocol.error as e:
					ARCTool.getStatusBar().showMessage(
325
						"Couldn't search mailbox: "+str(e), 5000
Cage, Marshall Andrew's avatar
Cage, Marshall Andrew committed
326
327
328
					)
				else:
					ARCTool.getStatusBar().showMessage(
329
						"Fetching Messages..."
Cage, Marshall Andrew's avatar
Cage, Marshall Andrew committed
330
331
					)
					self.emails = []
332
333
334
335
336
337
					_ = 1
					nums = data[0].split()
					for num in nums:
						ARCTool.getStatusBar().showMessage(
							"Fetching Message %d of %d..." %(_,len(nums))
						)
Cage, Marshall Andrew's avatar
Cage, Marshall Andrew committed
338
339
340
341
342
343
344
						typ, data = M.fetch(num, '(RFC822)')
						self.emails.append(
							email.message_from_bytes(data[0][1])
						)
						id = self.emails[-1].get('Message-ID')
						if id:
							self.emailIds[id] = self.emails[-1]
345
						_ +=1
Cage, Marshall Andrew's avatar
Cage, Marshall Andrew committed
346
347
348
					M.close()
			except protocol.error as e:
				ARCTool.getStatusBar().showMessage(
349
					"Couldn't select mailbox: "+str(e), 5000
Cage, Marshall Andrew's avatar
Cage, Marshall Andrew committed
350
351
352
353
354
355
				)
				return -1

		ARCTool.getStatusBar().showMessage(
			"Fetched %d message%s" %(len(self.emails),
				'' if len(self.emails) == 1 else 's'
356
357
			),
			5000
Cage, Marshall Andrew's avatar
Cage, Marshall Andrew committed
358
359
360
361
362
363
364
		)
		self.fetched = True
		return 0

	def setIgHeader(self, b):
		self.igHeader = b

365
366
367
	def setIgPles(self, b):
		self.igPles = b

Cage, Marshall Andrew's avatar
Cage, Marshall Andrew committed
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
	def setIgReplies(self, b):
		self.igReplies = b

	def setIgDup(self, b):
		self.igDup = b

	def setIgFirstDup(self, b):
		self.igFirstDup = b

	def setIgImages(self, b):
		self.igImages = b

	def setIgFormat(self, b):
		self.igFormat = b

	def setIgSpace(self, b):
		self.igSpace = b

	def updateDelim(self):
		self.delim = self.widget.delimeterEdit.text()

	def stripHeaders(self,message,text):
		text = re.sub('(?P<p><p )?.*?(?:%s):.+(?(p)[^`]*?</p>)\n?'\
			%(self.headers),'',text)
		return text

394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
	def stripPleasantries(self,text):
		return text

		# deltas = []
		# blocks = re.split('<br/?>',text)
		# if len(blocks) == 1:
		# 	return text

		# print('enough blocks')
		# for b in blocks[:]:
		# 	_b = re.sub(r'(?s)\s*<.+?>\s*', '',b)
		# 	_b = re.sub('\xa0',' ',_b)
		# 	_b = re.sub(r'&nbsp;',' ',_b)
		# 	if len(re.split(r'\b',_b)) < 4:
				# blocks.remove(b)
		# print(blocks)
		# return ''.join(blocks)
		# breaks = re.findall('<br/?>',text)
		# blockIndex = [
		# 	len(blocks[x]) + len(breaks[x]) for x in range(len(breaks))
		# ] + [len(blocks[-1])]
		# print('block indicies', blockIndex)
		# for i in range(1,len(blocks)):
		# 	blockIndex[i] += blockIndex[i-1]

		# for b in blocks:
		# 	b = re.sub(r'(?s)\s*<.+?>\s*', '',b)
		
		# wc = len(blocks[0])
		# for i in range(1,len(blocks)):
		# 	deltas.append( abs(len(blocks[i]) - len(blocks[i-1])) )
		# 	wc = len(blocks[i])
		# avg = wc/len(blocks)

		# deltaN = sum(deltas) / (2*wc)
		# blockLens = [len(b) for b in blocks]
		
		# if deltaN > avg/max(blockLens):
		# 	asc = 0
		# 	while deltas[asc] < avg:
		# 		asc += 1
		# 	des = len(deltas) - 1
		# 	# Naive approach, should really check to see if other islands exist
		# 	while des > asc and deltas[des] < avg:
		# 		des -= 1

		# 	print('start/stop block index', asc, des)
		# 	text = text[blockIndex[asc]:blockIndex[des]]
		# return text

Cage, Marshall Andrew's avatar
Cage, Marshall Andrew committed
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
	def stripImages(self,text):
		text = re.sub('(?s)<img .+?(?:/>|</img>)','',text)
		return text

	def collapseSpace(self,text):
		# Collapse Spaces
		text = re.sub('\xa0',' ',text)
		text = re.sub(' +',' ',text)

		# Collapse Breaks
		text = re.sub(r'<br>\s*</br>','<br/>',text)
		text = re.sub(r'(?<=>)\s*<br\s*/>\s*(?=</)', '',text)
		text = re.sub(r'\s*<span( [^>]+)?>\s*</span>\s*','',text)
		text = re.sub(r'\s*<p( [^>]+)?>\s*</p>\s*','',text)

		return text

	def stripReplies(self,message,text):
		ids = message.get("References")
		if ids:
			ids = re.split(',| ',ids)
			ids = [i.strip() for i in ids if i != '']
			# print(ids)
			for id in ids:
				if id in self.emailIds:
					# Remove this previous emails content from me
					ref = ''
					for part in self.emailIds[id].walk():
						typ = part.get_content_type()
						dis = part.get('Content-Disposition')
						if dis != 'attachment':
							if typ == 'text/plain' or typ == 'text/html':
								ref = part.get_payload(decode=True)\
									.decode('utf-8')
					# if self.igHeader:
					# 	ref = self.stripHeaders(self.emailIds[id[-2]],ref)

					bodyText = re.search('(?s)<body[^>]*?>(.+)</body>',text)
					bodyRef = re.search('(?s)<body[^>]*?>(.+)</body>',ref)
					if bodyText and bodyRef:
						bodyText = bodyText.group(1).strip()
						container = text.split(bodyText)
						bodyRef = bodyRef.group(1).strip()
						bodyText = re.sub('\xa0',' ',bodyText)
						bodyRef = re.sub('\xa0',' ',bodyRef)
						bodyTags = re.findall(r'\s*<.+?>\s*',bodyText)
						bodyText = re.sub(r'\s*<.+?>\s*',chr(1),bodyText)
						bodyRef = [re.escape(p) for p in \
							re.split(r'\s*<.+?>\s*',bodyRef) if p != '']
						bodyRef = '(?s)' + (chr(1)+'+').join(bodyRef)
						bodyRef = re.sub(r'(\\\s)+',r'\\s+',bodyRef)

						# Search for the original message within the reply
						partial = re.search(bodyRef,bodyText)
						if partial:
							excise = partial.group(0).count(chr(1))
							offset =\
								bodyText[:bodyText.find(partial.group(0))]\
								.count(chr(1))
							bodyText = bodyText.replace(partial.group(0),'')
							bodyTags = (bodyTags[:offset]
										+ bodyTags[offset+excise:])
							# Replace the tags
							for t in bodyTags:
								bodyText = bodyText.replace(chr(1),t,1)
							text = container[0] + bodyText + container[1]
						# We messed up? Impossible...
						# else:
						# 	print(bodyText)
						# 	print('-------vvvvvv------')
						# 	print(bodyRef)
		return text

	def stripDuplicate(self, text):
		num = self.widget.dupStrength.value()
		globs = {}
		body = re.search('(?s)<body[^>]*?>(.+)</body>',text).group(1)
		container = text.split(body)
		tags = re.findall(r'(?s)\s*<.+?>\s*',body)
523
		# Replace tags
Cage, Marshall Andrew's avatar
Cage, Marshall Andrew committed
524
		stripped = re.sub(r'(?s)\s*<.+?>\s*',chr(1),body)
525
		# Replace 
Cage, Marshall Andrew's avatar
Cage, Marshall Andrew committed
526
527
		stripped = re.sub('\xa0',' ',stripped)
		stripped = re.sub(r'&nbsp;',' ',stripped)
528
529
530
		spaces = re.findall(r'(?s)\s+',stripped)
		stripped = re.sub(r'(?s)\s+',r' ',stripped)
		print("stripped")
Cage, Marshall Andrew's avatar
Cage, Marshall Andrew committed
531
		_ = []
532
533
534
		# for word in re.finditer(r'(?:^| )(.+?)(?:(?= )|$)',stripped):
		for word in re.finditer(r'(?:\b)(.+?)(?:\b)',stripped):
		# for word in re.finditer(r'(?:\s)(.+?)(?:\s)',stripped):
Cage, Marshall Andrew's avatar
Cage, Marshall Andrew committed
535
536
537
538
539
540
541
542
			_.append((word.group(1),word.start(1),word.end(1)))
			if len(_) == num:
				hsh = ''.join(x[0].replace(chr(1),'') for x in _).__hash__()
				if hsh not in globs:
					globs[hsh] = []
				globs[hsh].append((_[0][1],_[-1][2]))
				_.pop(0)

543
		print("globbed")
Cage, Marshall Andrew's avatar
Cage, Marshall Andrew committed
544
545
546
547
		chains = []
		ranges = []
		for d in globs:
			if len(globs[d]) > 1:
548
				ranges += globs[d][1 if self.igFirstDup else 0:]
Cage, Marshall Andrew's avatar
Cage, Marshall Andrew committed
549
550
551
552
553
		ranges.sort()
		for r in ranges:
			if len(chains) == 0:
				chains.append([r[0],r[1]])
				continue
554
			if r[0] <= chains[-1][1] and r[1] > chains[-1][1]:
Cage, Marshall Andrew's avatar
Cage, Marshall Andrew committed
555
				chains[-1][1] = r[1]
556
			elif r[0] > chains[-1][1]:
Cage, Marshall Andrew's avatar
Cage, Marshall Andrew committed
557
				chains.append([r[0],r[1]])
558
559
		print("chained")
		# Only remove the text but keep the tags
Cage, Marshall Andrew's avatar
Cage, Marshall Andrew committed
560
		offset = 0
561
		# print('#chains=',len(chains))
Cage, Marshall Andrew's avatar
Cage, Marshall Andrew committed
562
563
564
565
566
567
		for c in chains:
			# Could partition, but I want variable names
			chunk = stripped[c[0]-offset:c[1]-offset]
			head = stripped[:c[0]-offset]
			tail = stripped[c[1]-offset:]
			# print(chunk)
568
569
570
			lh, lt = len(head), len(tail)
			# print(lh, lt, lh-lt)

Cage, Marshall Andrew's avatar
Cage, Marshall Andrew committed
571
572
573
			tagsRemoved = chunk.count(chr(1))
			spaceRemoved = chunk.count(' ')
			offset += len(chunk) - tagsRemoved
574
575
			spaces = (spaces[:head.count(' ')]
					  + spaces[head.count(' ') + spaceRemoved:])
Cage, Marshall Andrew's avatar
Cage, Marshall Andrew committed
576
577

			stripped = head + chr(1)*tagsRemoved + tail
578
		print("excised")
Cage, Marshall Andrew's avatar
Cage, Marshall Andrew committed
579
580
581
582
583

		for s in spaces:
			stripped = stripped.replace(' ',s,1)
		for t in tags:
			stripped = stripped.replace(chr(1),t,1)
584
		print("replaced")
Cage, Marshall Andrew's avatar
Cage, Marshall Andrew committed
585
586

		return container[0] + stripped + container[1]