From 7f8d7a7dbb8b3f47f3578fd2883baa4a3b89da78 Mon Sep 17 00:00:00 2001
From: retiefjimm <retiefjimm@gmail.com>
Date: Mon, 11 Oct 2010 14:05:57 -0500
Subject: [PATCH] Add '\n' after each </p> and <br /> tag.  Extremely
 long(200k+) single line chapters (like ffnet gives) causes problems for nook.
 Also removed a little dead code from ffnet.py.

---
 ffnet.py  |  9 ++-------
 output.py | 19 +++++++++++++------
 2 files changed, 15 insertions(+), 13 deletions(-)

diff --git a/ffnet.py b/ffnet.py
index 94fd995..f3e101f 100644
--- a/ffnet.py
+++ b/ffnet.py
@@ -117,17 +117,12 @@ class FFNet(FanfictionSiteAdapter):
 	
 	def getText(self, url):
 		data = self._fetchUrl(url)
-		lines = data.split('\n')
-		
-		textbuf = ''
-		emit = False
-		
 		olddata = data
 		try:
 			data = data.decode('utf8')
 		except:
 			data = olddata
-		
+
 		try:
 			soup = bs.BeautifulStoneSoup(data)
 		except:
@@ -195,4 +190,4 @@ class FFA_UnitTests(unittest.TestCase):
 		text = f.getText(url)
 		self.assertTrue(text.find('Kale Resgerald at your service" He answered, "So, can we go now? Or do you want to') != -1)
 if __name__ == '__main__':
-	unittest.main()
\ No newline at end of file
+	unittest.main()
diff --git a/output.py b/output.py
index 4a5387c..8b412a9 100644
--- a/output.py
+++ b/output.py
@@ -136,7 +136,7 @@ class EPubFanficWriter(FanficWriter):
 		self.storyTitle = removeEntities(name)
 		self.name = makeAcceptableFilename(name)
 		self.directory = self.basePath + '/' + self.name
-		self.authorName = removeEntities(author)
+		self.authorName = removeEntities(author+" aa")
 
 		self.inmemory = inmemory
 		
@@ -195,14 +195,21 @@ class EPubFanficWriter(FanficWriter):
 			if t.name in ('center'):
 				t['class']=t.name
 				t.name='div'
-
-		allPs = self.soup.findAll(recursive=True)
-		for p in allPs:
-			if p.string != None and len(p.string.strip()) == 0 :
-				p.extract()
+			# removes paired, but empty tags.
+			if t.string != None and len(t.string.strip()) == 0 :
+				t.extract()
 
 		text = self.soup.__str__('utf8')
 		
+		# ffnet(& maybe others) gives the whole chapter text
+		# as one line.  This causes problems for nook(at
+		# least) when the chapter size starts getting big
+		# (200k+) Using Soup's prettify() messes up italics
+		# and such.  Done after soup extract so <p> and <br>
+		# tags are normalized.  Doing it here seems less evil
+		# than hacking BeautifulSoup, but it's debatable.
+		text = text.replace('</p>','</p>\n').replace('<br />','<br />\n')
+		
 		self._writeFile(fn, XHTML_START % (title, title))
 		self._writeFile(fn, text)
 		self._writeFile(fn, XHTML_END)