Index

lognestmonster / ca9821e

A general-purpose single-header C logging library and parser for event-based logs. (Incomplete)

Download | Refs | Commit Log | Files | README | LICENSE

Latest Commit

{#}TimeHashSubjectAuthor#(+)(-)GPG?
9101 Sep 2019 21:35ca9821einfile bufferingJosh Stockin1112N

Blob @ lognestmonster / parser / read.py

application/x-python5398 bytesdownload raw
1# lognestmonster Copyright (c) 2019 Joshua 'joshuas3' Stockin
2# <https://github.com/JoshuaS3/lognestmonster/>.
3
4
5# This file is part of lognestmonster.
6
7# lognestmonster is free software: you can redistribute it and/or modify
8# it under the terms of the GNU General Public License as published by
9# the Free Software Foundation, either version 3 of the License, or
10# (at your option) any later version.
11
12# lognestmonster is distributed in the hope that it will be useful,
13# but WITHOUT ANY WARRANTY; without even the implied warranty of
14# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
15# GNU General Public License for more details.
16
17# You should have received a copy of the GNU General Public License
18# along with lognestmonster. If not, see <https://www.gnu.org/licenses/>.
19
20import struct
21import os
22import resource
23import time
24import sys
25
26STATEMENT_START = 0
27STATEMENT_END = 1
28EVENT_START = 2
29EVENT_END = 3
30
31VERBOSITY_LEVELS = {
32 0: "INIT",
33 1: "DEBUG",
34 2: "VERBOSE",
35 3: "VERYVERBOSE",
36 4: "WARNING",
37 5: "ERROR"
38}
39
40def ulonglong(bytestr):
41 return struct.unpack("@Q", bytestr)[0]
42def uchar(charv):
43 return struct.unpack("@B", charv)[0]
44def ushort(shortv):
45 return struct.unpack("@H", shortv)[0]
46
47
48class EventProto:
49 parent = None
50 pushed = []
51 def __init__(self):
52 self.parent = None
53 self.pushed = []
54
55class Reader:
56 fd = None
57
58 version = 0
59 timestamp = 0
60
61 top_level = []
62
63 event_count = 0
64 statement_count = 0
65
66 file_size = 0
67 position = 0
68 bad_bytes = 0
69
70 filter_time_start = -1
71 filter_time_end = -1
72 filter_verbosity = -1
73 filter_tag = -1
74
75 def __init__(self, fd):
76 self.fd = fd
77
78 self.version = 0
79 self.timestamp = 0
80
81 self.top_level = []
82
83 self.event_count = 0
84 self.statement_count = 0
85
86 self.file_size = 0
87 self.position = 0
88 self.bad_bytes = 0
89
90 self.filter_time_start = -1
91 self.filter_time_end = -1
92 self.filter_verbosity = -1
93 self.filter_tag = -1
94
95 def size(self):
96 self.fd.seek(0, os.SEEK_END) # go to end of file and get position
97 newsize = self.fd.tell()
98 self.fd.seek(self.position) # return to previous position
99
100 is_diff = self.file_size is not newsize
101 self.file_size = newsize
102 return is_diff
103
104 def pos(self):
105 self.position = self.fd.tell()
106 return self.position
107
108 def seek(self, position):
109 self.position = position
110 self.fd.seek(self.position)
111
112 def read(self, byte_count):
113 data = self.fd.read(byte_count)
114 if len(data) == byte_count:
115 return data
116 else:
117 return False
118
119 def scan(self): # scan for events and statements from self.position to the end of file
120 print()
121 print("beginning file scan")
122 print("file size: {0}".format(self.file_size))
123 print()
124
125 s = time.time()
126
127 if self.position == 0: # if it's the start of the file, grab version and timestamp
128 self.version = uchar(self.read(1))
129 self.timestamp = ulonglong(self.read(8))
130
131 current_statement = None
132 current_event = None
133
134 if self.position < self.file_size: # if the seeker is before EOF
135 while self.position < self.file_size: # while the seeker is before EOF
136 in_byte = uchar(self.read(1)) # read 1 byte
137
138 if in_byte == STATEMENT_START: # the byte indicates a statement's start, begin interpreting
139 self.statement_count += 1
140
141 new_statement = self.position
142
143 timestamp = ulonglong(self.read(8))
144 verbosity = uchar(self.read(1))
145
146 tag_size = uchar(self.read(1))
147 tag = self.read(tag_size).decode("utf-8")
148
149 append = True
150 if self.filter_time_start is not -1:
151 if timestamp < self.filter_time_start: append = False
152 if self.filter_time_end is not -1:
153 if timestamp > self.filter_time_end: append = False
154 if self.filter_verbosity is not -1:
155 if verbosity is not self.filter_verbosity: append = False
156 if self.filter_tag is not -1:
157 if tag is not self.filter_tag: append = False
158
159 message_size = ushort(self.read(2))
160 self.seek(self.pos() + message_size) # ignore the message
161
162 while uchar(self.read(1)) is not STATEMENT_END and self.pos() < self.file_size:
163 self.bad_bytes += 1
164
165 if append:
166 if current_event is not None:
167 current_event.pushed.append(new_statement)
168 else:
169 self.top_level.append(new_statement)
170
171 elif in_byte == EVENT_START: # the byte indicates an event's start, create an event
172 self.event_count += 1
173 new_event = EventProto()
174 if current_event is not None: # if an event exists, push the new event to it
175 new_event.parent = current_event
176 current_event.pushed.append(new_event)
177 current_event = new_event
178
179
180 elif in_byte == EVENT_END: # the byte indicates an event's end, close event if exists
181 if current_event is not None: # if an event exists
182 if current_event.parent is not None:
183 current_event = current_event.parent # if the event has a parent, set the parent to current
184 else:
185 self.top_level.append(current_event) # event has no parent, it's a top-level log item
186 current_event = None
187
188 else:
189 self.bad_bytes += 1
190
191 self.pos() # update seeker position for next byte (if not EOF)
192
193 print()
194 print("finished reading, {0} bad bytes".format(self.bad_bytes))
195 print()
196 print("version {0}".format(self.version))
197 print("timestamp {0}".format(self.timestamp))
198 print("event count {0}".format(self.event_count))
199 print("statement count {0}".format(self.statement_count))
200 print("time: {0}".format(time.time() - s))
201
202