pass2bw/pass2csv

#!/usr/bin/env python3
import argparse
import csv
import logging
import pathlib
import re
import sys

import gnupg

logging.basicConfig(level=logging.INFO)


def set_meta(entry, path, grouping_base):
    pure_path = pathlib.PurePath(path)
    group = pure_path.relative_to(grouping_base).parent
    if group.name == '':
        group = ''
    entry['group'] = group
    entry['title'] = pure_path.stem


def set_data(entry, data, exclude, get_fields, get_lines):
    lines = data.splitlines()
    tail = lines[1:]
    entry['password'] = lines[0]

    filtered_tail = []
    for line in tail:
        for exclude_pattern in exclude:
            if exclude_pattern.search(line):
                break
        else:
            filtered_tail.append(line)

    matching_indices = set()
    fields = entry.setdefault('fields', {})

    for i, line in enumerate(filtered_tail):
        for name, pattern in get_fields:
            if name in fields:
                # multiple patterns with same name, we've already found a match
                continue
            match = pattern.search(line)
            if not match:
                continue
            inverse_match = line[0:match.start()] + line[match.end():]
            value = inverse_match.strip()
            fields[name] = value
            matching_indices.add(i)
            break

    matching_lines = {}
    for i, line in enumerate(filtered_tail):
        for name, pattern in get_lines:
            match = pattern.search(line)
            if not match:
                continue
            matches = matching_lines.setdefault(name, [])
            matches.append(line)
            matching_indices.add(i)
            break
    for name, matches in matching_lines.items():
        fields[name] = '\n'.join(matching_lines)

    final_tail = []
    for i, line in enumerate(filtered_tail):
        if i not in matching_indices:
            final_tail.append(line)

    entry['notes'] = '\n'.join(final_tail).strip()


def write(file, entries, get_fields, get_lines):
    get_field_names = set(x[0] for x in get_fields)
    get_line_names = set(x[0] for x in get_lines)
    field_names = get_field_names | get_line_names
    header = ["Group(/)", "Title", "Password", *field_names, "Notes"]
    csvw = csv.writer(file)
    logging.info("Writing data to %s", file.name)
    csvw.writerow(header)
    for entry in entries:
        fields = [entry['fields'].get(name) for name in field_names]
        columns = [
            entry['group'], entry['title'], entry['password'],
            *fields,
            entry['notes']
        ]
        csvw.writerow(columns)


def main(store_path, grouping_base, outfile, gpgbinary, use_agent, encoding,
         exclude, get_fields, get_lines):
    entries = []
    failures = []
    path = pathlib.Path(store_path)
    grouping_path = pathlib.Path(grouping_base)
    gpg = gnupg.GPG(gpgbinary=gpgbinary, use_agent=use_agent)
    gpg.encoding = encoding
    for file in path.glob('**/*.gpg'):
        logging.info("Processing %s", file)
        with open(file, 'rb') as fp:
            decrypted = gpg.decrypt_file(fp)
        if not decrypted.ok:
            logging.error("Could not decrypt %s: %s", file, decrypted.status)
            failures.append((file, decrypted.status))
            continue
        entry = {}
        set_meta(entry, file, grouping_path)
        set_data(entry, str(decrypted), exclude, get_fields, get_lines)
        entries.append(entry)
    if failures:
        for file, status in failures:
            logging.warning("Could not decrypt %s: %s", file, status)
    write(outfile, entries, get_fields, get_lines)


def parse_args(args):
    class ExtendAction(argparse.Action):
        # Python 3.8 has 'extend' built in.
        def __call__(self, parser, namespace, values, option_string=None):
            items = getattr(namespace, self.dest) or []
            items.extend(values)
            setattr(namespace, self.dest, items)

    parser = argparse.ArgumentParser()
    parser.add_argument(
        'store_path',
        type=str,
        help="path to the password-store to export",
    )

    parser.add_argument(
        '-b', '--base',
        metavar='path',
        type=str,
        help="path to use as base for grouping passwords",
        dest='base_path'
    )

    parser.add_argument(
        '-g', '--gpg',
        metavar='executable',
        type=str,
        default="gpg",
        help="path to the gpg binary you wish to use (default 'gpg')",
        dest='gpgbinary'
    )

    parser.add_argument(
        '-a', '--use-agent',
        action='store_true',
        default=False,
        help="ask gpg to use its auth agent",
        dest='use_agent'
    )

    parser.add_argument(
        '--encoding',
        metavar='encoding',
        type=str,
        default="utf-8",
        help="text encoding to use when reading gpg output (default 'utf-8')",
        dest='encoding'
    )

    parser.add_argument(
        '-o', '--outfile',
        metavar='file',
        type=argparse.FileType('w'),
        default="-",
        help="file to write exported data to (default stdin)",
        dest='outfile'
    )

    parser.add_argument(
        '-e', '--exclude',
        metavar='pattern',
        action=ExtendAction,
        nargs='+',
        type=str,
        default=[],
        help="regexps for lines which should not be exported",
        dest='exclude'
    )

    parser.add_argument(
        '-f', '--get-field',
        metavar=('name', 'pattern'),
        action='append',
        nargs=2,
        type=str,
        default=[],
        help=(
            "a name and a regexp, the part of the line matching the regexp"
            " will be removed and the remaining line will be added to a field"
            " with the chosen name. only one match per password, matching"
            " stops after the first match"
        ),
        dest='get_fields'
    )

    parser.add_argument(
        '-l', '--get-line',
        metavar=('name', 'pattern'),
        action='append',
        nargs=2,
        type=str,
        default=[],
        help=(
            "a name and a regexp for which all lines that match are included"
            " in a field with the chosen name"
        ),
        dest='get_lines'
    )

    return parser.parse_args(args)


def compile_regexp(pattern):
    try:
        regexp = re.compile(pattern, re.I)
    except re.error as e:
        logging.error(
            "Could not compile pattern '%s', %s at position %s",
            pattern.replace("'", "\\'"), e.msg, e.pos
        )
        return None
    return regexp


if __name__ == '__main__':
    parsed = parse_args(sys.argv[1:])

    failed = False
    exclude_patterns = []
    for pattern in parsed.exclude:
        regexp = compile_regexp(pattern)
        if not regexp:
            failed = True
        exclude_patterns.append(regexp)

    get_fields = []
    for name, pattern in parsed.get_fields:
        regexp = compile_regexp(pattern)
        if not regexp:
            failed = True
        get_fields.append((name, regexp))

    get_lines = []
    for name, pattern in parsed.get_lines:
        regexp = compile_regexp(pattern)
        if not regexp:
            failed = True
        get_lines.append((name, regexp))

    if failed:
        sys.exit(1)

    if parsed.base_path:
        grouping_base = parsed.base_path
    else:
        grouping_base = parsed.store_path

    kwargs = {
        'store_path': parsed.store_path,
        'grouping_base': grouping_base,
        'gpgbinary': parsed.gpgbinary,
        'use_agent': parsed.use_agent,
        'encoding': parsed.encoding,
        'outfile': parsed.outfile,
        'exclude': exclude_patterns,
        'get_fields': get_fields,
        'get_lines': get_lines
    }

    main(**kwargs)