def test_extensions_order_ascii_only(self):
ascii_filename = '12345.txt'
self.request_head_response(valid_files=[ascii_filename])
extensions = text._format_download_uri(12345)
self.assertEqual(extensions.split('/')[-1], ascii_filename)
extensions = text._format_download_uri(12345, prefer_ascii=True)
self.assertEqual(extensions.split('/')[-1], ascii_filename)
def test_extensions_order_ascii_only(self):
ascii_filename = '12345.txt'
self.request_head_response(valid_files=[ascii_filename])
extensions = text._format_download_uri(12345)
self.assertEqual(extensions.split('/')[-1], ascii_filename)
extensions = text._format_download_uri(12345, prefer_ascii=True)
self.assertEqual(extensions.split('/')[-1], ascii_filename)
def test_extensions_order_ascii_first(self):
ascii_filename = '12345.txt'
all_files = ['12345-8.txt', '12345-0.txt', '12345.txt']
self.request_head_response(valid_files=all_files)
extensions = text._format_download_uri(12345)
self.assertNotEqual(extensions.split('/')[-1], ascii_filename)
extensions = text._format_download_uri(12345, prefer_ascii=True)
self.assertEqual(extensions.split('/')[-1], ascii_filename)
def test_extensions_order_ascii_first(self):
ascii_filename = '12345.txt'
all_files = ['12345-8.txt', '12345-0.txt', '12345.txt']
self.request_head_response(valid_files=all_files)
extensions = text._format_download_uri(12345)
self.assertNotEqual(extensions.split('/')[-1], ascii_filename)
extensions = text._format_download_uri(12345, prefer_ascii=True)
self.assertEqual(extensions.split('/')[-1], ascii_filename)
total_spaces = 0
accepted = 0
for i, book in enumerate(meta):
if i + 1 % 10 == 0:
sys.stderr.write("\rSeen " + str(i + 1) + " books, accepted " +
str(accepted) + " with " + str(total_spaces) +
" spaces ")
book_id, title, author = book.split("\t")
try:
e_text = load_etext(int(book_id),
mirror="http://gutenberg.readingroo.ms")
url = _format_download_uri(int(book_id),
mirror="http://gutenberg.readingroo.ms")
except: # can't find URI, e.g. UnknownDownloadUriException
sys.stderr.write("WARN: could not download text ID:" + str(book_id) +
"\n")
continue
text = strip_headers(e_text).strip().replace("\r", "")
# Collapse multiline brackets (e.g. multiline figure captions)
collapsed = ""
lines = text.split("\n")
open_bracket = False
for line in lines:
if "[" in line and not "]" in line:
open_bracket = True
if open_bracket: