dinislage/web2py
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

many pep8 improvements

Browse Source
This commit is contained in:
mdipierro
2012-10-19 12:33:53 -05:00
parent 71ec15190b
commit 6aa5edc7ff
117 changed files with 7160 additions and 5670 deletions
Download Patch File Download Diff File Expand all files Collapse all files
gluon/decoder.py
+27 -24
View File
@@ -1,4 +1,5 @@
import codecs, encodings
import codecs
import encodings
"""Caller will hand this library a buffer and ask it to either convert
it or auto-detect the type.
@@ -9,16 +10,17 @@ Licensed under the PSF License
"""
# None represents a potentially variable byte. "##" in the XML spec...
autodetect_dict={ # bytepattern : ("name",
(0x00, 0x00, 0xFE, 0xFF) : ("ucs4_be"),
(0xFF, 0xFE, 0x00, 0x00) : ("ucs4_le"),
(0xFE, 0xFF, None, None) : ("utf_16_be"),
(0xFF, 0xFE, None, None) : ("utf_16_le"),
(0x00, 0x3C, 0x00, 0x3F) : ("utf_16_be"),
(0x3C, 0x00, 0x3F, 0x00) : ("utf_16_le"),
(0x3C, 0x3F, 0x78, 0x6D): ("utf_8"),
(0x4C, 0x6F, 0xA7, 0x94): ("EBCDIC")
}
autodetect_dict = { # bytepattern : ("name",
(0x00, 0x00, 0xFE, 0xFF): ("ucs4_be"),
(0xFF, 0xFE, 0x00, 0x00): ("ucs4_le"),
(0xFE, 0xFF, None, None): ("utf_16_be"),
(0xFF, 0xFE, None, None): ("utf_16_le"),
(0x00, 0x3C, 0x00, 0x3F): ("utf_16_be"),
(0x3C, 0x00, 0x3F, 0x00): ("utf_16_le"),
(0x3C, 0x3F, 0x78, 0x6D): ("utf_8"),
(0x4C, 0x6F, 0xA7, 0x94): ("EBCDIC")
}
def autoDetectXMLEncoding(buffer):
""" buffer -> encoding_name
@@ -31,14 +33,14 @@ def autoDetectXMLEncoding(buffer):
# buffer at once but otherwise we'd have to decode a character at
# a time looking for the quote character...that's a pain
encoding = "utf_8" # according to the XML spec, this is the default
encoding = "utf_8" # according to the XML spec, this is the default
# this code successively tries to refine the default
# whenever it fails to refine, it falls back to
# the last place encoding was set.
if len(buffer)>=4:
if len(buffer) >= 4:
bytes = (byte1, byte2, byte3, byte4) = tuple(map(ord, buffer[0:4]))
enc_info = autodetect_dict.get(bytes, None)
if not enc_info: # try autodetection again removing potentially
if not enc_info: # try autodetection again removing potentially
# variable bytes
bytes = (byte1, byte2, None, None)
enc_info = autodetect_dict.get(bytes)
@@ -46,29 +48,30 @@ def autoDetectXMLEncoding(buffer):
enc_info = None
if enc_info:
encoding = enc_info # we've got a guess... these are
encoding = enc_info # we've got a guess... these are
#the new defaults
# try to find a more precise encoding using xml declaration
secret_decoder_ring = codecs.lookup(encoding)[1]
(decoded,length) = secret_decoder_ring(buffer)
(decoded, length) = secret_decoder_ring(buffer)
first_line = decoded.split("\n")[0]
if first_line and first_line.startswith(u"<?xml"):
encoding_pos = first_line.find(u"encoding")
if encoding_pos!=-1:
if encoding_pos != -1:
# look for double quote
quote_pos=first_line.find('"', encoding_pos)
quote_pos = first_line.find('"', encoding_pos)
if quote_pos==-1: # look for single quote
quote_pos=first_line.find("'", encoding_pos)
if quote_pos == -1: # look for single quote
quote_pos = first_line.find("'", encoding_pos)
if quote_pos>-1:
quote_char,rest=(first_line[quote_pos],
first_line[quote_pos+1:])
encoding=rest[:rest.find(quote_char)]
if quote_pos > -1:
quote_char, rest = (first_line[quote_pos],
first_line[quote_pos + 1:])
encoding = rest[:rest.find(quote_char)]
return encoding
def decoder(buffer):
encoding = autoDetectXMLEncoding(buffer)
return buffer.decode(encoding).encode('utf8')