FilesExpand file tree

 master

/

merge-rulesets.py

Copy path

Blame

More file actions

Blame

More file actions

Latest commit

 

History

History

History

106 lines (82 loc) · 3.33 KB

 master

/

merge-rulesets.py

Copy path

Top

File metadata and controls

• Code
• Blame

106 lines (82 loc) · 3.33 KB

Raw

Copy raw file

Download raw file

Open symbols panel

Edit and raw actions

1

2

3

4

5

6

7

8

9

10

11

12

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

38

39

40

41

42

43

44

45

46

47

48

49

50

51

52

53

54

55

56

57

58

59

60

61

62

63

64

65

66

67

68

69

70

71

72

73

74

75

76

77

78

79

80

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

#!/usr/bin/env python3.6

# Merge all the .xml rulesets into a single "default.rulesets" file -- this

# prevents inodes from wasting disk space, but more importantly, this works

# around the fact that zip does not perform well on a pile of small files.

# Currently, it merges rulesets into a JSON Object for minimal overhead,

# in both storage and parsing speed.

import argparse

import glob

import json

import os

import unicodedata

import xml.etree.ElementTree

def normalize(f):

"""

OSX and Linux filesystems encode composite characters differently in

filenames. We should normalize to NFC: http://unicode.org/reports/tr15/

"""

f = unicodedata.normalize("NFC", f)

return f

# commandline arguments parsing (nobody use it, though)

parser = argparse.ArgumentParser(description="Merge rulesets")

parser.add_argument("--source_dir", default="src/chrome/content/rules")

args = parser.parse_args()

# output filename, pointed to the merged ruleset

ofn = os.path.join(args.source_dir, "default.rulesets")

# XML Ruleset Files

files = map(normalize, glob.glob(os.path.join(args.source_dir, "*.xml")))

# Under git bash, sed -i issues errors and sets the file "read-only".

if os.path.isfile(ofn):

os.system("chmod u+w " + ofn)

# Library (JSON Object)

library = []

# Parse XML ruleset and construct JSON library

print(" * Parsing XML ruleset and constructing JSON library...")

for filename in sorted(files):

tree = xml.etree.ElementTree.parse(filename)

root = tree.getroot()

ruleset = {}

trivialNameSecureCookie = None

for attr in root.attrib:

ruleset[attr] = root.attrib[attr]

for child in root:

if child.tag in ["target", "rule", "securecookie", "exclusion"]:

if child.tag not in ruleset:

ruleset[child.tag] = []

else:

continue

if child.tag == "target":

ruleset["target"].append(child.attrib["host"])

elif child.tag == "rule":

ru = {}

ru["from"] = child.attrib["from"]

ru["to"] = child.attrib["to"]

ruleset["rule"].append(ru)

elif child.tag == "securecookie":

if child.attrib["name"] == ".+":

if not trivialNameSecureCookie:

trivialNameSecureCookie = {}

trivialNameSecureCookie["host"] = child.attrib["host"]

trivialNameSecureCookie["name"] = ".+"

else:

trivialNameSecureCookie["host"] = (trivialNameSecureCookie["host"] + "|" + child.attrib["host"])

else:

sc = {}

sc["host"] = child.attrib["host"]

sc["name"] = child.attrib["name"]

ruleset["securecookie"].append(sc)

elif child.tag == "exclusion":

if len(ruleset["exclusion"]) == 0:

ruleset["exclusion"].append(child.attrib["pattern"])

else:

ruleset["exclusion"][0] = (ruleset["exclusion"][0] + "|" + child.attrib["pattern"])

if trivialNameSecureCookie:

ruleset["securecookie"].insert(0, trivialNameSecureCookie)

library.append(ruleset);

# Write to default.rulesets

print(" * Writing JSON library to %s" % ofn)

outfile = open(ofn, "w")

outfile.write(json.dumps(library, separators=(",", ":")))

outfile.close()

# Everything is okay.

print(" * Everything is okay.")