pre-commit-hooks/pre_commit_hooks/pretty_format_json.py

import argparse
import json
import sys
from difflib import unified_diff
from typing import List
from typing import Mapping
from typing import Optional
from typing import Sequence
from typing import Tuple
from typing import Union

INFINITY = float('inf')


def _make_iterencode(
    markers, _default, _encoder, _indent, _floatstr,
    _key_separator, _item_separator, _sort_keys, _skipkeys,
    _one_shot,
    ## HACK: hand-optimized bytecode; turn globals into locals
    ValueError=ValueError,
    dict=dict,
    float=float,
    id=id,
    int=int,
    isinstance=isinstance,
    list=list,
    str=str,
    tuple=tuple,
    _intstr=int.__str__,
):

    if _indent is not None and not isinstance(_indent, str):
        _indent = ' ' * _indent

    def _iterencode_list(lst, _current_indent_level):
        if not lst:
            yield '[]'
            return
        if markers is not None:
            markerid = id(lst)
            if markerid in markers:
                raise ValueError('Circular reference detected')
            markers[markerid] = lst
        buf = '['
        if _indent is not None:
            _current_indent_level += 1
            newline_indent = '\n' + _indent * _current_indent_level
            separator = _item_separator.rstrip() + newline_indent
            buf += newline_indent
        else:
            newline_indent = None
            separator = _item_separator
        first = True
        for value in lst:
            if first:
                first = False
            else:
                buf = separator
            if isinstance(value, str):
                yield buf + _encoder(value)
            elif value is None:
                yield buf + 'null'
            elif value is True:
                yield buf + 'true'
            elif value is False:
                yield buf + 'false'
            elif isinstance(value, int):
                # Subclasses of int/float may override __str__, but we still
                # want to encode them as integers/floats in JSON. One example
                # within the standard library is IntEnum.
                yield buf + _intstr(value)
            elif isinstance(value, float):
                # see comment above for int
                yield buf + _floatstr(value)
            else:
                yield buf
                if isinstance(value, (list, tuple)):
                    chunks = _iterencode_list(value, _current_indent_level)
                elif isinstance(value, dict):
                    chunks = _iterencode_dict(value, _current_indent_level)
                else:
                    chunks = _iterencode(value, _current_indent_level)
                yield from chunks
        if newline_indent is not None:
            _current_indent_level -= 1
            yield '\n' + _indent * _current_indent_level
        yield ']'
        if markers is not None:
            del markers[markerid]

    def _iterencode_dict(dct, _current_indent_level):
        if not dct:
            yield '{}'
            return
        _indent = None  # No newlines or indentation for the k-v pairs.
        if markers is not None:
            markerid = id(dct)
            if markerid in markers:
                raise ValueError('Circular reference detected')
            markers[markerid] = dct
        yield '{'
        if _indent is not None:
            _current_indent_level += 1
            newline_indent = '\n' + _indent * _current_indent_level
            item_separator = _item_separator + newline_indent
            yield newline_indent
        else:
            newline_indent = None
            item_separator = _item_separator
        first = True
        if _sort_keys:
            items = sorted(dct.items(), key=lambda kv: kv[0])
        else:
            items = dct.items()
        for key, value in items:
            if isinstance(key, str):
                pass
            # JavaScript is weakly typed for these, so it makes sense to
            # also allow them.  Many encoders seem to do something like this.
            elif isinstance(key, float):
                # see comment for int/float in _make_iterencode
                key = _floatstr(key)
            elif key is True:
                key = 'true'
            elif key is False:
                key = 'false'
            elif key is None:
                key = 'null'
            elif isinstance(key, int):
                # see comment for int/float in _make_iterencode
                key = _intstr(key)
            elif _skipkeys:
                continue
            else:
                raise TypeError(
                    f'keys must be str, int, float, bool or None, '
                    f'not {key.__class__.__name__}',
                )
            if first:
                first = False
            else:
                yield item_separator
            yield _encoder(key)
            yield _key_separator
            if isinstance(value, str):
                yield _encoder(value)
            elif value is None:
                yield 'null'
            elif value is True:
                yield 'true'
            elif value is False:
                yield 'false'
            elif isinstance(value, int):
                # see comment for int/float in _make_iterencode
                yield _intstr(value)
            elif isinstance(value, float):
                # see comment for int/float in _make_iterencode
                yield _floatstr(value)
            else:
                if isinstance(value, (list, tuple)):
                    chunks = _iterencode_list(value, _current_indent_level)
                elif isinstance(value, dict):
                    chunks = _iterencode_dict(value, _current_indent_level)
                else:
                    chunks = _iterencode(value, _current_indent_level)
                yield from chunks
        if newline_indent is not None:
            _current_indent_level -= 1
            yield '\n' + _indent * _current_indent_level
        yield '}'
        if markers is not None:
            del markers[markerid]

    def _iterencode(o, _current_indent_level):
        if isinstance(o, str):
            yield _encoder(o)
        elif o is None:
            yield 'null'
        elif o is True:
            yield 'true'
        elif o is False:
            yield 'false'
        elif isinstance(o, int):
            # see comment for int/float in _make_iterencode
            yield _intstr(o)
        elif isinstance(o, float):
            # see comment for int/float in _make_iterencode
            yield _floatstr(o)
        elif isinstance(o, (list, tuple)):
            yield from _iterencode_list(o, _current_indent_level)
        elif isinstance(o, dict):
            yield from _iterencode_dict(o, _current_indent_level)
        else:
            if markers is not None:
                markerid = id(o)
                if markerid in markers:
                    raise ValueError('Circular reference detected')
                markers[markerid] = o
            o = _default(o)
            yield from _iterencode(o, _current_indent_level)
            if markers is not None:
                del markers[markerid]
    return _iterencode


class CustomJSONEncoder(json.JSONEncoder):
    def iterencode(self, o, _one_shot=False):
        """Encode the given object and yield each string
        representation as available.

        For example::

            for chunk in JSONEncoder().iterencode(bigobject):
                mysocket.write(chunk)

        """
        if self.check_circular:
            markers = {}
        else:
            markers = None

        def floatstr(
            o, allow_nan=self.allow_nan,
            _repr=float.__repr__, _inf=INFINITY, _neginf=-INFINITY,
        ):
            # Check for specials.  Note that this type of test is processor
            # and/or platform-specific, so do tests which don't depend on the
            # internals.

            if o != o:
                text = 'NaN'
            elif o == _inf:
                text = 'Infinity'
            elif o == _neginf:
                text = '-Infinity'
            else:
                return _repr(o)

            if not allow_nan:
                raise ValueError(
                    'Out of range float values are not JSON compliant: ' +
                    repr(o),
                )

            return text

        _encoder = json.encoder.py_encode_basestring

        _iterencode = _make_iterencode(
            markers, self.default, _encoder, self.indent, floatstr,
            self.key_separator, self.item_separator, self.sort_keys,
            self.skipkeys, _one_shot,
        )
        return _iterencode(o, 0)


def _get_pretty_format(
        contents: str,
        indent: str,
        ensure_ascii: bool = True,
        sort_keys: bool = True,
        top_keys: Sequence[str] = (),
        sort_by_first_key: bool = False,
) -> str:
    def pairs_first(pairs: Sequence[Tuple[str, str]]) -> Mapping[str, str]:
        before = [pair for pair in pairs if pair[0] in top_keys]
        before = sorted(before, key=lambda x: top_keys.index(x[0]))
        after = [pair for pair in pairs if pair[0] not in top_keys]
        if sort_keys:
            after.sort()
        return dict(before + after)

    json_contents = json.loads(contents, object_pairs_hook=pairs_first)
    if sort_by_first_key:
        json_contents.sort(key=lambda row: list(row.values())[0])
    json_pretty = json.dumps(
        json_contents,
        indent=indent,
        ensure_ascii=ensure_ascii,
        cls=CustomJSONEncoder,
        separators=(', ', ': '),
    )
    return f'{json_pretty}\n'


def _autofix(filename: str, new_contents: str) -> None:
    print(f'Fixing file {filename}')
    with open(filename, 'w', encoding='UTF-8') as f:
        f.write(new_contents)


def parse_num_to_int(s: str) -> Union[int, str]:
    """Convert string numbers to int, leaving strings as is."""
    try:
        return int(s)
    except ValueError:
        return s


def parse_topkeys(s: str) -> List[str]:
    return s.split(',')


def get_diff(source: str, target: str, file: str) -> str:
    source_lines = source.splitlines(True)
    target_lines = target.splitlines(True)
    diff = unified_diff(source_lines, target_lines, fromfile=file, tofile=file)
    return ''.join(diff)


def main(argv: Optional[Sequence[str]] = None) -> int:
    parser = argparse.ArgumentParser()
    parser.add_argument(
        '--autofix',
        action='store_true',
        dest='autofix',
        help='Automatically fixes encountered not-pretty-formatted files',
    )
    parser.add_argument(
        '--indent',
        type=parse_num_to_int,
        default='2',
        help=(
            'The number of indent spaces or a string to be used as delimiter'
            ' for indentation level e.g. 4 or "\t" (Default: 2)'
        ),
    )
    parser.add_argument(
        '--no-ensure-ascii',
        action='store_true',
        dest='no_ensure_ascii',
        default=False,
        help=(
            'Do NOT convert non-ASCII characters to Unicode escape sequences '
            '(\\uXXXX)'
        ),
    )
    parser.add_argument(
        '--no-sort-keys',
        action='store_true',
        dest='no_sort_keys',
        default=False,
        help='Keep JSON nodes in the same order',
    )
    parser.add_argument(
        '--top-keys',
        type=parse_topkeys,
        dest='top_keys',
        default=[],
        help='Ordered list of keys to keep at the top of JSON hashes',
    )
    parser.add_argument(
        '--sort-by-first-key',
        dest='sort_by_first_key',
        action='store_true',
        default=False,
        help='Sort the json by a specific key',
    )
    parser.add_argument('filenames', nargs='*', help='Filenames to fix')
    args = parser.parse_args(argv)

    status = 0

    for json_file in args.filenames:
        with open(json_file, encoding='UTF-8') as f:
            contents = f.read()

        try:
            pretty_contents = _get_pretty_format(
                contents, args.indent, ensure_ascii=not args.no_ensure_ascii,
                sort_keys=not args.no_sort_keys, top_keys=args.top_keys,
                sort_by_first_key=args.sort_by_first_key,
            )
        except ValueError:
            print(
                f'Input File {json_file} is not a valid JSON, consider using '
                f'check-json',
            )
            return 1

        if contents != pretty_contents:
            if args.autofix:
                _autofix(json_file, pretty_contents)
            else:
                diff_output = get_diff(contents, pretty_contents, json_file)
                sys.stdout.buffer.write(diff_output.encode())

            status = 1

    return status


if __name__ == '__main__':
    exit(main())