mirror/antizapret-pac-generator-light
1
0
Fork 0
mirror of https://bitbucket.org/anticensority/antizapret-pac-generator-light.git synced 2024-11-22 05:06:04 +03:00
Code Issues Packages Projects Releases Wiki Activity

Improve topsequence compression algorithm

Browse Source
This commit is contained in:
ValdikSS 2024-01-06 03:12:44 +03:00
parent b0073641a1
commit bf2cb905ec
1 changed files with 52 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

63
scripts/topsequences.py
View File

@ -12,37 +12,78 @@ if len(sys.argv) != 4:
print("{}: <host list.txt> <awk output.awk> <pac function.js>".format(sys.argv[0])) print("{}: <host list.txt> <awk output.awk> <pac function.js>".format(sys.argv[0]))
sys.exit(1) sys.exit(1)
#patternhit = {"cloudfront": 999999999}
patternhit = {} patternhit = {}
# "&" character should be prepended with two backslashes for awk's gsub. # "&" character should be prepended with two backslashes for awk's gsub.
wordreplace=["A", "B", "C", "D", "E", "F", "G", "H", "I", "J", wordreplace=["A", "B", "C", "D", "E", "F", "G", "H", "I", "J",
"K", "L", "M", "N", "O", "P", "Q", "R", "S", "T", "K", "L", "M", "N", "O", "P", "Q", "R", "S", "T",
"U", "V", "W", "X", "Y", "Z", "U", "V", "W", "X", "Y", "Z",
"!", "@", "#", "$", "%", "^", "\\\\&", "*", "(", ")", "@", "#", "$", "%", "^", "\\\\&", "*", "(", ")",
"=", "+", "/", ",", "<", ">", "~", "[", "]", "{", "}"] "=", "+", "/", ",", "<", ">", "~", "[", "]", "{", "}",
"`", ":", ";", "?"]
wordreplace_big = ["!" + chr(x) for x in range(ord("A"), ord("Z") + 1)]
with open(sys.argv[1], "r") as dfile: with open(sys.argv[1], "r") as dfile:
domains = dfile.read().split("\n") domains = dfile.read().split("\n")
new_domains = [] new_domains = []
for domain in domains: for domain in domains:
#print('.'.join(domain.split(".")[:-1]))
#sys.exit(1)
new_domains.append('.'.join(domain.split(".")[:-1])) new_domains.append('.'.join(domain.split(".")[:-1]))
domains = ''.join(new_domains) domains = ''.join(new_domains)
domain_len = len(domains) domain_len = len(domains)
position = 0 position = 0
while position <= domain_len: pattern_found = {}
cut = domains[position:position+2]
if not patternhit.get(cut):
patternhit[cut] = 0
patternhit[cut] += 1
position += 2
patternhit = dict(sorted(patternhit.items(), key=lambda x: x[1])) for patternlen in (4,):
for round, _ in enumerate(wordreplace_big):
position = 0
while position <= domain_len:
cut = domains[position:position+patternlen]
position += 1
if len(cut) != patternlen:
continue
if not patternhit.get(cut):
patternhit[cut] = 0
patternhit[cut] += 1
#print("Round", round, "patternhit", patternhit)
patternhit = dict(sorted(patternhit.items(), key=lambda x: len(x[0]) * x[1])[-1:])
domains = domains.replace(list(patternhit.keys())[0], '')
pattern_found.update(patternhit)
patternhit = {}
print("Big round", round, "pattern_found", pattern_found)
for patternlen in (2,):
for round, _ in enumerate(wordreplace):
position = 0
while position <= domain_len:
cut = domains[position:position+patternlen]
position += 1
if len(cut) != patternlen:
continue
if not patternhit.get(cut):
patternhit[cut] = 0
patternhit[cut] += 1
#print("Round", round, "patternhit", patternhit)
patternhit = dict(sorted(patternhit.items(), key=lambda x: len(x[0]) * x[1])[-1:])
domains = domains.replace(list(patternhit.keys())[0], '')
pattern_found.update(patternhit)
patternhit = {}
print("Round", round, "pattern_found", pattern_found)
#patternhit = dict(sorted(patternhit.items(), key=lambda x: len(x[0]) * x[1]))
patternhit = pattern_found
print(patternhit)
#print(patternhit, file=sys.stderr) #print(patternhit, file=sys.stderr)
finallist = list(patternhit)[-1 * len(wordreplace):] #finallist = list(patternhit)[:len(wordreplace)]
#print(finallist, file=sys.stderr) finallist = list(patternhit)
#finallist.reverse()
print(finallist, file=sys.stderr)
wordreplace = wordreplace_big + wordreplace
with open(sys.argv[2], "w") as awkfile: with open(sys.argv[2], "w") as awkfile:
print("{", file=awkfile) print("{", file=awkfile)