mirror of
https://github.com/gosticks/wordpress-develop.git
synced 2026-06-28 14:20:15 +00:00
Ensure svn:eol-style is consistently set for all files.
See #42594. git-svn-id: https://develop.svn.wordpress.org/trunk@46586 602fd350-edb4-49c9-b593-d223f7449a82
This commit is contained in:
File diff suppressed because it is too large
Load Diff
@@ -1,33 +1,33 @@
|
||||
# Generates urlencoded.txt from utf-8.txt
|
||||
#
|
||||
# urlencoded.txt is used by Tests_Formatting_Utf8UriEncode
|
||||
|
||||
import urllib, codecs, re
|
||||
import sys
|
||||
|
||||
# uncapitalize pct-encoded values, leave the rest alone
|
||||
capfix = re.compile("%([0-9A-Z]{2})");
|
||||
def fix(match):
|
||||
octet = match.group(1)
|
||||
intval = int(octet, 16)
|
||||
if intval < 128:
|
||||
return chr(intval).lower()
|
||||
return '%' + octet.lower()
|
||||
|
||||
def urlencode(line):
|
||||
"""Percent-encode each byte of non-ASCII unicode characters."""
|
||||
line = urllib.quote(line.strip().encode("utf-8"))
|
||||
line = capfix.sub(fix, line)
|
||||
return line
|
||||
|
||||
if __name__ == "__main__":
|
||||
args = sys.argv[1:]
|
||||
if args and args[0] in ("-h", "--help"):
|
||||
print "Usage: python urlencode.py < utf-8.txt > urlencoded.txt"
|
||||
sys.exit(2)
|
||||
|
||||
sys.stdin = codecs.getreader("utf-8")(sys.stdin)
|
||||
sys.stdout = codecs.getwriter("ascii")(sys.stdout)
|
||||
|
||||
lines = sys.stdin.readlines()
|
||||
sys.stdout.write( "\n".join(map(urlencode, lines)) )
|
||||
# Generates urlencoded.txt from utf-8.txt
|
||||
#
|
||||
# urlencoded.txt is used by Tests_Formatting_Utf8UriEncode
|
||||
|
||||
import urllib, codecs, re
|
||||
import sys
|
||||
|
||||
# uncapitalize pct-encoded values, leave the rest alone
|
||||
capfix = re.compile("%([0-9A-Z]{2})");
|
||||
def fix(match):
|
||||
octet = match.group(1)
|
||||
intval = int(octet, 16)
|
||||
if intval < 128:
|
||||
return chr(intval).lower()
|
||||
return '%' + octet.lower()
|
||||
|
||||
def urlencode(line):
|
||||
"""Percent-encode each byte of non-ASCII unicode characters."""
|
||||
line = urllib.quote(line.strip().encode("utf-8"))
|
||||
line = capfix.sub(fix, line)
|
||||
return line
|
||||
|
||||
if __name__ == "__main__":
|
||||
args = sys.argv[1:]
|
||||
if args and args[0] in ("-h", "--help"):
|
||||
print "Usage: python urlencode.py < utf-8.txt > urlencoded.txt"
|
||||
sys.exit(2)
|
||||
|
||||
sys.stdin = codecs.getreader("utf-8")(sys.stdin)
|
||||
sys.stdout = codecs.getwriter("ascii")(sys.stdout)
|
||||
|
||||
lines = sys.stdin.readlines()
|
||||
sys.stdout.write( "\n".join(map(urlencode, lines)) )
|
||||
|
||||
@@ -1,27 +1,27 @@
|
||||
# Generates test data for functions converting between
|
||||
# dodgy windows-1252-only values and their unicode counterparts
|
||||
|
||||
unichars = ["201A", "0192", "201E", "2026", "2020", "2021",
|
||||
"02C6", "2030", "0160", "2039", "0152", "2018",
|
||||
"2019", "201C", "201D", "2022", "2013", "2014",
|
||||
"02DC", "2122", "0161", "203A", "0153", "0178"];
|
||||
|
||||
winpoints = []
|
||||
unipoints = []
|
||||
|
||||
for char in unichars:
|
||||
char = unichr(int(char, 16))
|
||||
dec = ord(char)
|
||||
win = ord(char.encode("windows-1252"))
|
||||
|
||||
unipoints.append(dec)
|
||||
winpoints.append(win)
|
||||
|
||||
def entitize(s):
|
||||
return "&#%s;" % s
|
||||
|
||||
winpoints = map(entitize, winpoints)
|
||||
unipoints = map(entitize, unipoints)
|
||||
|
||||
print "".join(winpoints), "".join(unipoints)
|
||||
|
||||
# Generates test data for functions converting between
|
||||
# dodgy windows-1252-only values and their unicode counterparts
|
||||
|
||||
unichars = ["201A", "0192", "201E", "2026", "2020", "2021",
|
||||
"02C6", "2030", "0160", "2039", "0152", "2018",
|
||||
"2019", "201C", "201D", "2022", "2013", "2014",
|
||||
"02DC", "2122", "0161", "203A", "0153", "0178"];
|
||||
|
||||
winpoints = []
|
||||
unipoints = []
|
||||
|
||||
for char in unichars:
|
||||
char = unichr(int(char, 16))
|
||||
dec = ord(char)
|
||||
win = ord(char.encode("windows-1252"))
|
||||
|
||||
unipoints.append(dec)
|
||||
winpoints.append(win)
|
||||
|
||||
def entitize(s):
|
||||
return "&#%s;" % s
|
||||
|
||||
winpoints = map(entitize, winpoints)
|
||||
unipoints = map(entitize, unipoints)
|
||||
|
||||
print "".join(winpoints), "".join(unipoints)
|
||||
|
||||
|
||||
Reference in New Issue
Block a user