Updated grepper.

This commit is contained in:
Michael Herzberg 2017-09-27 14:05:16 +01:00
parent 2cfeb9b88c
commit f37e19f46a
2 changed files with 29 additions and 33 deletions

1
extfind.py Symbolic link
View File

@ -0,0 +1 @@
extfind

61
grepper
View File

@ -28,6 +28,8 @@ from zipfile import ZipFile
from functools import partial
import re
from ExtensionCrawler.config import const_basedir
from extfind import iter_extension_paths, iter_extension_paths_from_file
def help():
print("grepper [OPTION] GREP [FILE]")
@ -36,7 +38,7 @@ def help():
print(" -h print this help text")
print(" -b beautify JavaScript before matching")
print(" -a <DIR> archive directory")
print(" -p <PREFIX> three-letter-prefix")
print(" -g <GLOB> glob on the extenion id, don't use with -e")
print(" -e <EXTIDFILELIST> file with extension ids")
print(" -t <THREADS> number of threads to use")
print(" -n <TASKID> process chunk n where n in [1,N]")
@ -54,6 +56,12 @@ def guarded_stderr(string):
sys.stderr.write(string)
lock.release()
def has_at_least_one_match(content, pattern):
for line in content.splitlines():
if re.search(pattern, line):
return True
return False
def process_crx(ext_id, date, crx, pattern, beautify):
try:
@ -64,7 +72,8 @@ def process_crx(ext_id, date, crx, pattern, beautify):
with z.open(zip_file_info) as f:
content = f.read().decode(errors="surrogateescape")
if beautify:
content = jsbeautifier.beautify(content)
if has_at_least_one_match(content, pattern):
content = jsbeautifier.beautify(content)
for i, line in enumerate(content.splitlines()):
if not re.search(pattern, line):
continue
@ -93,24 +102,6 @@ def process_id(pattern, beautify, path):
path, traceback.format_exc()))
def find(archive, pattern):
for root, _, files in os.walk(os.path.join(archive, "data")):
for file in files:
if fnmatch.fnmatch(file, pattern + ".tar"):
yield os.path.join(root, file)
def find_from_file(archive, extidlistfile):
with open(extidlistfile, 'r') as f:
extids = [l.strip() for l in f.readlines()]
for root, _, files in os.walk(os.path.join(archive, "data")):
for file in files:
for extid in extids:
if fnmatch.fnmatch(file, extid + ".tar"):
yield os.path.join(root, file)
def init(l):
global lock
lock = l
@ -120,13 +111,16 @@ def parse_args(argv):
archive = const_basedir()
beautify = False
parallel = 8
extidglob = None
extidlistfile = None
taskid = 1
maxtaskid = 1
paths = []
try:
opts, args = getopt.getopt(argv, "ha:p:e:bt:n:N:", [
"archive=", "prefix=", "extidlistfile=", "beautify", "threads=",
"archive=", "glob=", "extidlistfile=", "beautify", "threads=",
"taskid=", "maxtaskid="
])
except getopt.GetoptError:
@ -138,12 +132,10 @@ def parse_args(argv):
sys.exit()
elif opt in ("-a", "--archive"):
archive = arg
elif opt in ("-p", "--prefix"):
prefix = arg
paths += find(archive, prefix + "*")
elif opt in ("-g", "--glob"):
extidglob = arg
elif opt in ("-e", "--extidlistfile"):
extidlistfile = arg
paths += find_from_file(archive, extidlistfile)
elif opt in ("-b", "--beautify"):
beautify = True
elif opt in ("-t", "--threads"):
@ -158,15 +150,18 @@ def parse_args(argv):
sys.exit(2)
pattern = args[0]
paths += args[1:]
if paths == []:
paths = list(find(archive, "*"))
chunksize = int(len(paths) / maxtaskid)
if taskid == maxtaskid:
paths = paths[(taskid - 1) * chunksize:]
if len(args) > 1:
paths = args[1:]
elif extidglob is None and extidlistfile is None:
paths = iter_extension_paths(archive, taskid, maxtaskid)
elif extidglob is None and extidlistfile is not None:
paths = iter_extension_paths_from_file(archive, taskid, maxtaskid,
extidlistfile)
elif extidglob is not None and extidlistfile is None:
paths = iter_extension_paths(archive, taskid, maxtaskid, extidglob)
else:
paths = paths[(taskid - 1) * chunksize:taskid * chunksize]
help()
sys.exit(2)
return pattern, paths, beautify, parallel