#!/usr/bin/python3

# The MIT License (MIT)
#
# Copyright © 2024 pacman64
#
# Permission is hereby granted, free of charge, to any person obtaining a copy
# of this software and associated documentation files (the “Software”), to deal
# in the Software without restriction, including without limitation the rights
# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
# copies of the Software, and to permit persons to whom the Software is
# furnished to do so, subject to the following conditions:
#
# The above copyright notice and this permission notice shall be included in
# all copies or substantial portions of the Software.
#
# THE SOFTWARE IS PROVIDED “AS IS”, WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
# SOFTWARE.


from shutil import copyfileobj
from sys import argv, exit, stderr, stdin, stdout
from typing import List


info = '''
dog [options...] [filepaths/URIs...]

This script reads/fetches all named sources given to it, which can be a mix
of filepaths and URIs. Its name suggests that, unlike `cat`, it can also
fetch URIs.

Any of `-l`, `--l`, `-lines`, or `--lines` enables line-mode, which ensures
each non-empty input ends with a line feed, even when the original data do
not; this mode also ignores leading UTF-8 BOM on first lines, and turns all
CRLF byte-pairs into simple line-feeds. In other words, line-mode ensures
unix-style output lines.

The help option is `-h`, `--h`, `-help`, or `--help`.
'''

# a leading help-option arg means show the help message and quit
if len(argv) == 2 and argv[1] in ('-h', '--h', '-help', '--help'):
    print(info.strip(), file=stderr)
    exit(0)


def seems_url(s: str) -> bool:
    protocols = ('https://', 'http://', 'file://', 'ftp://', 'data:')
    return any(s.startswith(p) for p in protocols)


def bytes_mode(args: List[str]) -> None:
    dashes = 0
    data = bytes()
    reuse_stdin = args.count('-') > 1

    if any(seems_url(e) for e in args):
        from urllib.request import urlopen

    for path in args:
        if path == '-':
            dashes += 1
            if reuse_stdin and dashes == 1:
                data = stdin.buffer.read()
            if reuse_stdin:
                stdout.buffer.write(data)
                stdout.flush()
                continue
            copyfileobj(stdin.buffer, stdout.buffer)
            stdout.flush()
            continue

        if seems_url(path):
            with urlopen(path) as inp:
                copyfileobj(inp, stdout.buffer)
            stdout.flush()
            continue

        with open(path, mode='rb') as inp:
            copyfileobj(inp, stdout.buffer)
        stdout.flush()

    if len(args) == 0:
        copyfileobj(stdin.buffer, stdout.buffer)
        stdout.flush()


def lines_mode(args: List[str]) -> None:
    dashes = 0
    lines = []
    reuse_stdin = args.count('-') > 1

    if any(seems_url(e) for e in args):
        from urllib.request import urlopen

    for path in args:
        if path == '-':
            dashes += 1
            if reuse_stdin and dashes == 1:
                lines = load_lines(stdin, '\xef\xbb\xbf', '\r\n', '\n')
            if reuse_stdin:
                for line in lines:
                    stdout.write(line)
                    stdout.write('\n')
                stdout.flush()
                continue
            emit_lines(stdout, stdin, '\xef\xbb\xbf', '\r\n', '\n')
            stdout.flush()
            continue

        if seems_url(path):
            with urlopen(path) as inp:
                w = stdout.buffer
                emit_lines(w, inp, b'\xef\xbb\xbf', b'\r\n', b'\n')
            stdout.flush()
            continue

        with open(path, encoding='utf-8') as inp:
            emit_lines(stdout, inp, '\xef\xbb\xbf', '\r\n', '\n')
        stdout.flush()

    if len(args) == 0:
        emit_lines(stdout, stdin, '\xef\xbb\xbf', '\r\n', '\n')
        stdout.flush()


def load_lines(src, utf8bom, crlf, lf) -> List[str]:
    lines = []
    first = True
    for line in src:
        line = line.lstrip(utf8bom) if first else line
        # ignore trailing carriage-returns and line-feeds in lines
        lines.append(line.rstrip(crlf).rstrip(lf))
        first = False
    return lines


def emit_lines(w, src, utf8bom, crlf, lf) -> None:
    first = True
    for line in src:
        line = line.lstrip(utf8bom) if first else line
        # ignore trailing carriage-returns and line-feeds in lines
        w.write(line.rstrip(crlf).rstrip(lf))
        w.write(lf)
        first = False


try:
    if len(argv) > 1 and argv[1] in ('-l', '--l', '-lines', '--lines'):
        lines_mode(argv[2:])
    else:
        bytes_mode(argv[1:])
except BrokenPipeError:
    # quit quietly, instead of showing a confusing error message
    stderr.close()
except KeyboardInterrupt:
    exit(2)
except Exception as e:
    print(f'\x1b[31m{e}\x1b[0m', file=stderr)
    exit(1)