| 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 |
|
| 20 | import struct |
| 21 | import os |
| 22 |
|
| 23 | STATEMENT_START = 0 |
| 24 | STATEMENT_END = 1 |
| 25 | EVENT_START = 2 |
| 26 | EVENT_END = 3 |
| 27 |
|
| 28 | VERBOSITY_LEVELS = { |
| 29 | 0: "INIT", |
| 30 | 1: "DEBUG", |
| 31 | 2: "VERBOSE", |
| 32 | 3: "VERYVERBOSE", |
| 33 | 4: "WARNING", |
| 34 | 5: "ERROR" |
| 35 | } |
| 36 |
|
| 37 | def ulonglong(bytestr): |
| 38 | return struct.unpack("@Q", bytestr)[0] |
| 39 | def uchar(charv): |
| 40 | return struct.unpack("@B", charv)[0] |
| 41 | def ushort(shortv): |
| 42 | return struct.unpack("@H", shortv)[0] |
| 43 |
|
| 44 |
|
| 45 | class EventProto: |
| 46 | parent = None |
| 47 | pushed = [False] |
| 48 | def __init__(self): |
| 49 | self.parent = None |
| 50 | self.pushed = [False] |
| 51 |
|
| 52 | class Reader: |
| 53 | fd = None |
| 54 |
|
| 55 | top_level = [] |
| 56 |
|
| 57 | current_event = None |
| 58 |
|
| 59 | event_count = 0 |
| 60 | statement_count = 0 |
| 61 |
|
| 62 | seekable = True |
| 63 | file_size = 0 |
| 64 | position = 0 |
| 65 |
|
| 66 | version = 0 |
| 67 | timestamp = 0 |
| 68 |
|
| 69 | bad_bytes = 0 |
| 70 |
|
| 71 | filter_time_start = -1 |
| 72 | filter_time_end = -1 |
| 73 | filter_verbosity = -1 |
| 74 | filter_tag = -1 |
| 75 |
|
| 76 | update_callbacks = [] |
| 77 |
|
| 78 | def __init__(self, fd, seekable=True): |
| 79 | self.fd = fd |
| 80 |
|
| 81 | self.top_level = [] |
| 82 |
|
| 83 | self.current_event = None |
| 84 |
|
| 85 | self.event_count = 0 |
| 86 | self.statement_count = 0 |
| 87 |
|
| 88 | self.seekable = seekable |
| 89 | self.file_size = 0 |
| 90 | self.position = 0 |
| 91 |
|
| 92 | self.version = 0 |
| 93 | self.timestamp = 0 |
| 94 |
|
| 95 | self.bad_bytes = 0 |
| 96 |
|
| 97 | self.filter_time_start = -1 |
| 98 | self.filter_time_end = -1 |
| 99 | self.filter_verbosity = -1 |
| 100 | self.filter_tag = -1 |
| 101 |
|
| 102 | self.update_callbacks = [] |
| 103 |
|
| 104 | def update(self): |
| 105 | for callback in self.update_callbacks: |
| 106 | callback() |
| 107 |
|
| 108 | def onupdate(self, callback): |
| 109 | self.update_callbacks.append(callback) |
| 110 |
|
| 111 | def size(self): |
| 112 | self.fd.seek(0, os.SEEK_END) # go to end of file and get position |
| 113 | newsize = self.fd.tell() |
| 114 | self.fd.seek(self.position) # return to previous position |
| 115 |
|
| 116 | is_diff = self.file_size is not newsize |
| 117 | self.file_size = newsize |
| 118 | return is_diff |
| 119 |
|
| 120 | def pos(self): |
| 121 | p = self.fd.tell() |
| 122 | self.position = p |
| 123 | return p |
| 124 |
|
| 125 | def seek(self, position): |
| 126 | self.position = position |
| 127 | self.fd.seek(self.position) |
| 128 |
|
| 129 | def read(self, byte_count): |
| 130 | return self.fd.read(byte_count) |
| 131 |
|
| 132 | def fetch_item(self, position): |
| 133 | previouspos = self.pos() |
| 134 | self.seek(position) |
| 135 | timestamp = ulonglong(self.read(8)) |
| 136 | verbosity = uchar(self.read(1)) |
| 137 | tag_size = uchar(self.read(1)) |
| 138 | tag = self.read(tag_size).decode("utf-8") |
| 139 | message_size = ushort(self.read(2)) |
| 140 | message = self.read(message_size).decode("utf-8") |
| 141 | self.seek(previouspos) |
| 142 | return (timestamp, verbosity, tag_size, tag, message_size, message) |
| 143 |
|
| 144 | def parse_block(self, in_byte): |
| 145 | if in_byte == STATEMENT_START: # the byte indicates a statement's start, begin interpreting |
| 146 | if self.seekable: |
| 147 | this_position = self.position + 1 # identify and save the seeker position of this statement |
| 148 |
|
| 149 | try: |
| 150 | timestamp = ulonglong(self.read(8)) |
| 151 | verbosity = uchar(self.read(1)) |
| 152 | tag_size = uchar(self.read(1)) |
| 153 | tag = self.read(tag_size).decode("utf-8") |
| 154 | |
| 155 | append = True |
| 156 |
|
| 157 | if self.filter_time_start is not -1 and append: |
| 158 | append = timestamp > self.filter_time_start |
| 159 |
|
| 160 | if self.filter_time_end is not -1 and append: |
| 161 | append = timestamp < self.filter_time_end |
| 162 |
|
| 163 | if self.filter_verbosity is not -1 and append: |
| 164 | append = verbosity in self.filter_verbosity |
| 165 |
|
| 166 | if self.filter_tag is not -1 and append: |
| 167 | append = tag == self.filter_tag |
| 168 |
|
| 169 | message_size = ushort(self.read(2)) |
| 170 | if self.seekable: |
| 171 | self.read(message_size) |
| 172 | else: |
| 173 | message = self.read(message_size).decode("utf-8") |
| 174 | |
| 175 | if self.seekable: |
| 176 | while uchar(self.read(1)) is not STATEMENT_END and self.pos() < self.file_size: |
| 177 | self.bad_bytes += 1 |
| 178 | else: |
| 179 | while uchar(self.read(1)) is not STATEMENT_END: |
| 180 | self.bad_bytes += 1 |
| 181 |
|
| 182 | if append == True: |
| 183 | self.statement_count += 1 |
| 184 | self.update() |
| 185 | if self.current_event is not None: |
| 186 | if self.seekable: |
| 187 | self.current_event.pushed.append(this_position) |
| 188 | else: |
| 189 | self.current_event.pushed.append((timestamp, verbosity, tag_size, tag, message_size, message)) |
| 190 | else: |
| 191 | if self.seekable: |
| 192 | self.top_level.append(this_position) |
| 193 | else: |
| 194 | self.top_level.append((timestamp, verbosity, tag_size, tag, message_size, message)) |
| 195 | except: |
| 196 | return -1 |
| 197 |
|
| 198 | elif in_byte == EVENT_START: # the byte indicates an event's start, create an event |
| 199 | new_event = EventProto() |
| 200 | if self.current_event is not None: # we're already inside an event, set the new event's parent to match |
| 201 | new_event.parent = self.current_event |
| 202 | self.current_event = new_event |
| 203 |
|
| 204 |
|
| 205 | elif in_byte == EVENT_END: # end of event |
| 206 | if self.current_event is not None: |
| 207 | if len(self.current_event.pushed) > 1: |
| 208 | self.event_count += 1 |
| 209 | self.update() |
| 210 | if self.current_event.parent is not None: |
| 211 | self.current_event.parent.pushed.append(self.current_event) |
| 212 | self.current_event = self.current_event.parent |
| 213 | else: |
| 214 | self.top_level.append(self.current_event) |
| 215 | self.current_event = None |
| 216 | else: # event is empty |
| 217 | if self.current_event.parent is not None: |
| 218 | self.current_event = self.current_event.parent |
| 219 | else: |
| 220 | self.current_event = None |
| 221 | else: |
| 222 | self.bad_bytes += 1 # event doesn't exist, bad byte |
| 223 | return -1 |
| 224 |
|
| 225 | else: # unknown byte |
| 226 | self.bad_bytes += 1 |
| 227 | return -1 |
| 228 |
|
| 229 | def scan(self): # scan for events and statements from self.position to the end of file |
| 230 | if self.position == 0 and self.seekable: # if it's the start of the file, grab version and timestamp |
| 231 | self.version = uchar(self.read(1)) |
| 232 | self.timestamp = ulonglong(self.read(8)) |
| 233 |
|
| 234 | current_event = None |
| 235 |
|
| 236 | if self.pos() < self.file_size: # if the seeker is before EOF |
| 237 | while self.pos() < self.file_size: # while the seeker is before EOF |
| 238 | in_byte = uchar(self.read(1)) # read 1 byte |
| 239 | self.parse_block(in_byte) # parse block based on byte read |
| 240 |
|
| 241 |
|
Index