def is_database_directory(path: util.PathLike) -> bool:
"""
Return `True` if *path* is a valid TSDB database directory.
A path is a valid database directory if it is a directory
containing a schema file. This is a simple test; the schema file
itself is not checked for validity.
"""
path = Path(path).expanduser()
return path.is_dir() and path.joinpath(SCHEMA_FILENAME).is_file()
def write_schema(path: util.PathLike, schema: Schema) -> None:
"""
Serialize *schema* and write it to the relations file at *path*.
If *path* is a directory, write to a `relations` file under
*path*, otherwise write to the file *path*.
"""
path = Path(path).expanduser()
if path.is_dir():
path = path.joinpath(SCHEMA_FILENAME)
path.write_text(_format_schema(schema) + '\n')
def read_schema(path: util.PathLike) -> Schema:
"""
Instantiate schema dict from a schema file given by *path*.
If *path* is a directory, use the relations file under *path*. If
*path* is a file, use it directly as the schema's path. Otherwise
raise a :exc:`TSDBSchemaError`.
"""
path = Path(path).expanduser()
if path.is_dir():
path = path.joinpath(SCHEMA_FILENAME)
if not path.is_file():
raise TSDBSchemaError(f'no valid schema file at {path!s}')
return _parse_schema(path.read_text())
def write(dir: util.PathLike,
name: str,
records: Iterable[Record],
fields: Fields,
append: bool = False,
gzip: bool = False,
encoding: str = 'utf-8') -> None:
"""
Write *records* to relation *name* in the database at *dir*.
The simplest way to write data to a file would be something like
the following:
>>> with open(os.path.join(db.path, 'item'), 'w') as fh:
... print('\\n'.join(map(tsdb.join, db['item'])), file=fh)
This function improves on that method by doing the following:
* Determining the path from the *gzip* parameter and existing files
* Writing plain text or compressed data, as appropriate
* Appending or overwriting data, as requested
* Using the schema information to format fields
* Writing to a temporary file then copying when done; this
prevents accidental data loss when overwriting a file that is
being read
* Deleting any alternative (compressed or plain text) file to
avoid having inconsistent files (e.g., delete any existing
`item` when writing `item.gz`)
Note that *append* cannot be used with *gzip* or with an existing
gzipped file and in such a case a :exc:`NotImplementedError` will
be raised. This may be allowed in the future, but as appending to
a gzipped file (in general) results in inefficient compression, it
is better to append to plain text and compress when done.
Args:
dir: path to the database directory
name: name of the relation to write
records: iterable of records to write
fields: iterable of :class:`Field` objects
append: if `True`, append to rather than overwrite the file
gzip: if `True` and the file is not empty, compress the file
with `gzip`; if `False`, do not compress
encoding: character encoding of the file
Example:
>>> tsdb.write('my-profile',
... 'item',
... item_records,
... schema['item'])
"""
dir = Path(dir).expanduser()
if encoding is None:
encoding = 'utf-8'
if not dir.is_dir():
raise TSDBError(f'invalid test suite directory: {dir}')
tx_path, gz_path, use_gz = _get_paths(dir, name)
if append and (gzip or use_gz):
raise NotImplementedError('cannot append to a gzipped file')
mode = 'ab' if append else 'wb'
with tempfile.NamedTemporaryFile(mode='w+b',
suffix='.tmp',
prefix=name,
dir=dir) as f_tmp:
for record in records:
f_tmp.write((join(record, fields) + '\n').encode(encoding))
# only gzip non-empty files
gzip = gzip and f_tmp.tell() != 0
dest, other = (gz_path, tx_path) if gzip else (tx_path, gz_path)
# now copy the temp file to the destination
f_tmp.seek(0)
if gzip:
with gzopen(dest, mode) as f_out:
shutil.copyfileobj(f_tmp, f_out)
else:
with dest.open(mode=mode) as f_out:
shutil.copyfileobj(f_tmp, f_out)
# clean up other (gz or non-gz) file if it exists
if other.is_file():
other.unlink()