File: frep.py 1 #!/usr/bin/python3 2 3 # The MIT License (MIT) 4 # 5 # Copyright © 2024 pacman64 6 # 7 # Permission is hereby granted, free of charge, to any person obtaining a copy 8 # of this software and associated documentation files (the “Software”), to deal 9 # in the Software without restriction, including without limitation the rights 10 # to use, copy, modify, merge, publish, distribute, sublicense, and/or sell 11 # copies of the Software, and to permit persons to whom the Software is 12 # furnished to do so, subject to the following conditions: 13 # 14 # The above copyright notice and this permission notice shall be included in 15 # all copies or substantial portions of the Software. 16 # 17 # THE SOFTWARE IS PROVIDED “AS IS”, WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 18 # IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 19 # FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE 20 # AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 21 # LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, 22 # OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE 23 # SOFTWARE. 24 25 26 from math import ceil, log10 27 from re import compile as compile_re, IGNORECASE, Pattern 28 from sys import argv, exit, stderr, stdin, stdout 29 30 31 info = ''' 32 frep [options...] [regex] [filepaths/URIs...] 33 34 35 Flat Regular-Expression Print(er) shows all regex-matches on binary data, 36 without being limited by end-of-line-style byte-sequences. 37 38 Matches are always shown ANSI-styled, starting with the data-source name 39 (a filepath, or URI), the 0-based byte-offset range of the match, a few 40 preceding bytes, the bytes matched (styled), and a few following bytes, 41 the surrounding unstyled bytes shown for context. 42 43 All (optional) leading options start with either single or double-dash. 44 Some of the options are, shown in their single-dash form: 45 46 -h show this help message 47 -help show this help message 48 49 -i case-insensitive matching of ASCII letters 50 ''' 51 52 if len(argv) == 2 and argv[1] in ('-h', '--h', '-help', '--help'): 53 print(info.strip(), file=stderr) 54 exit(0) 55 56 57 def seems_url(s: str) -> bool: 58 protocols = ('https://', 'http://', 'file://', 'ftp://', 'data:') 59 return any(s.startswith(p) for p in protocols) 60 61 62 def handle_input(w, name: str, data: bytes, pat: Pattern) -> None: 63 pad = 20 64 o = w.write 65 l = len(data) 66 n = int(ceil(log10(l))) if l > 0 else 0 67 68 for m in pat.finditer(data): 69 i = m.start() 70 j = m.end() 71 72 s = f'\x1b[35m{name} \x1b[34m[{i:{0}>{n}}:{j:{0}>{n}}]\x1b[0m ' 73 o(s.encode('utf-8')) 74 o(data[(i - min(i, pad)):i]) 75 o(b'\x1b[48;5;29m\x1b[97m') 76 o(data[i:j]) 77 o(b'\x1b[0m') 78 o(data[j:min(l, j + pad)]) 79 o(b'\x1b[0m\n') 80 81 try: 82 mode = 0 # NOFLAG 83 start_inputs = 2 84 if len(argv) > 1 and argv[1] in ('-i', '--i'): 85 mode = IGNORECASE 86 start_inputs = 3 87 88 if len(argv) < start_inputs: 89 print(info.strip(), file=stderr) 90 raise ValueError('no regex given') 91 92 expr = compile_re(argv[start_inputs - 1].encode('utf-8'), flags=mode) 93 inputs = argv[start_inputs:] 94 95 if inputs.count('-') > 1: 96 msg = 'can\'t read from `-` (standard input) more than once' 97 raise ValueError(msg) 98 99 if any(seems_url(e) for e in inputs): 100 from urllib.request import urlopen 101 102 r = stdin.buffer 103 w = stdout.buffer 104 f = handle_input 105 106 for path in inputs: 107 if path == '-': 108 f(w, path, r.read(), expr) 109 continue 110 111 if seems_url(path): 112 with urlopen(path) as inp: 113 f(w, path, inp.read(), expr) 114 continue 115 116 with open(path, mode='rb') as inp: 117 f(w, path, inp.read(), expr) 118 119 if len(inputs) == 0: 120 f(w, '-', r.read(), expr) 121 except BrokenPipeError: 122 # quit quietly, instead of showing a confusing error message 123 stderr.close() 124 except KeyboardInterrupt: 125 exit(2) 126 except Exception as e: 127 print(f'\x1b[31m{e}\x1b[0m', file=stderr) 128 exit(1)