diff --git a/swh/scanner/dashboard/dashboard.py b/swh/scanner/dashboard/dashboard.py index 4bc6c29..1743401 100644 --- a/swh/scanner/dashboard/dashboard.py +++ b/swh/scanner/dashboard/dashboard.py @@ -1,101 +1,101 @@ # Copyright (C) 2020 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information from pathlib import Path import dash from dash.dependencies import Input, Output import dash_bootstrap_components as dbc import dash_core_components as dcc import dash_html_components as html import plotly.graph_objects as go from ..model import Tree def generate_table_body(dir_path: Path, source: Tree): """ Generate the data_table from the path taken from the chart. For each file builds the html table rows showing the known status, a local link to the file and the relative SoftWare Heritage persistent IDentifier (SWHID). """ data = [] - for file_info in source.getFilesFromDir(dir_path): + for file_info in source.get_files_from_dir(dir_path): for file_path, attr in file_info.items(): file_path = Path(file_path) file_name = file_path.parts[len(file_path.parts) - 1] data.append( html.Tr( [ html.Td("✔" if attr["known"] else ""), html.Td( html.A(file_name, href="file://" + str(file_path.resolve())) ), html.Td(attr["swhid"]), ] ) ) return [html.Tbody(data)] def run_app(graph_obj: go, source: Tree): app = dash.Dash(__name__) fig = go.Figure().add_trace(graph_obj) fig.update_layout(height=800,) table_header = [ html.Thead(html.Tr([html.Th("KNOWN"), html.Th("FILE NAME"), html.Th("SWHID")])) ] app.layout = html.Div( [ html.Div( [ html.Div( [dcc.Graph(id="sunburst_chart", figure=fig),], className="col", ), html.Div( [ html.H3(id="directory_title"), dbc.Table( id="files_table", hover=True, responsive=True, striped=True, ), ], className="col", ), ], className="row", ), ] ) @app.callback( [Output("files_table", "children"), Output("directory_title", "children")], [Input("sunburst_chart", "clickData")], ) def update_files_table(click_data): """ Callback that takes the input (directory path) from the chart and update the `files_table` children with the relative files. """ if click_data is not None: raw_path = click_data["points"][0]["label"] full_path = ( source.path.joinpath(raw_path) if raw_path != str(source.path) else Path(raw_path) ) return table_header + generate_table_body(full_path, source), str(full_path) else: return "", "" app.run_server(debug=True, use_reloader=True) diff --git a/swh/scanner/model.py b/swh/scanner/model.py index 78fb34c..7087ae3 100644 --- a/swh/scanner/model.py +++ b/swh/scanner/model.py @@ -1,265 +1,265 @@ # Copyright (C) 2020 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information from __future__ import annotations from enum import Enum import json from pathlib import Path import sys from typing import Any, Dict, Iterator, List, Tuple import ndjson from swh.model.identifiers import CONTENT, DIRECTORY from .exceptions import InvalidDirectoryPath, InvalidObjectType from .plot import generate_sunburst, offline_plot class Color(Enum): blue = "\033[94m" green = "\033[92m" red = "\033[91m" end = "\033[0m" def colorize(text: str, color: Color): return color.value + text + Color.end.value class Tree: """Representation of a file system structure """ def __init__(self, path: Path, father: Tree = None): self.father = father self.path = path self.otype = DIRECTORY if path.is_dir() else CONTENT self.swhid = "" self.known = False self.children: Dict[Path, Tree] = {} - def addNode(self, path: Path, swhid: str, known: bool) -> None: + def add_node(self, path: Path, swhid: str, known: bool) -> None: """Recursively add a new path. """ relative_path = path.relative_to(self.path) if relative_path == Path("."): self.swhid = swhid self.known = known return new_path = self.path.joinpath(relative_path.parts[0]) if new_path not in self.children: self.children[new_path] = Tree(new_path, self) - self.children[new_path].addNode(path, swhid, known) + self.children[new_path].add_node(path, swhid, known) - def show(self, format) -> None: + def show(self, fmt) -> None: """Show tree in different formats""" - if format == "json": - print(json.dumps(self.toDict(), indent=4, sort_keys=True)) + if fmt == "json": + print(json.dumps(self.to_dict(), indent=4, sort_keys=True)) - if format == "ndjson": - print(ndjson.dumps(dict_path for dict_path in self.__iterNodesAttr())) + if fmt == "ndjson": + print(ndjson.dumps(dict_path for dict_path in self._iter_nodes_attr())) - elif format == "text": + elif fmt == "text": isatty = sys.stdout.isatty() print(colorize(str(self.path), Color.blue) if isatty else str(self.path)) - self.printChildren(isatty) + self.print_children(isatty) - elif format == "sunburst": + elif fmt == "sunburst": root = self.path - directories = self.getDirectoriesInfo(root) + directories = self.get_directories_info(root) sunburst = generate_sunburst(directories, root) offline_plot(sunburst) - def printChildren(self, isatty: bool, inc: int = 1) -> None: + def print_children(self, isatty: bool, inc: int = 1) -> None: for path, node in self.children.items(): - self.printNode(node, isatty, inc) + self.print_node(node, isatty, inc) if node.children: - node.printChildren(isatty, inc + 1) + node.print_children(isatty, inc + 1) - def printNode(self, node: Any, isatty: bool, inc: int) -> None: + def print_node(self, node: Any, isatty: bool, inc: int) -> None: rel_path = str(node.path.relative_to(self.path)) begin = "│ " * inc end = "/" if node.otype == DIRECTORY else "" if isatty: if not node.known: rel_path = colorize(rel_path, Color.red) elif node.otype == DIRECTORY: rel_path = colorize(rel_path, Color.blue) elif node.otype == CONTENT: rel_path = colorize(rel_path, Color.green) print(f"{begin}{rel_path}{end}") @property def attributes(self) -> Dict[str, Dict[str, Any]]: """ Get the attributes of the current node grouped by the relative path. Returns: a dictionary containing a path as key and its known/unknown status and the SWHID as values. """ return {str(self.path): {"swhid": self.swhid, "known": self.known,}} - def toDict(self) -> Dict[str, Dict[str, Any]]: + def to_dict(self) -> Dict[str, Dict[str, Any]]: """ Recursively flatten the current tree nodes into a dictionary. For example, if you have the following structure: .. code-block:: none root { subdir: { file.txt } } The generated dictionary will be: .. code-block:: none { "root": { "swhid": "...", "known": True/False } "root/subdir": { "swhid": "...", "known": True/False } "root/subdir/file.txt": { "swhid": "...", "known": True/False } } """ - return {k: v for d in self.__iterNodesAttr() for k, v in d.items()} + return {k: v for d in self._iter_nodes_attr() for k, v in d.items()} def iterate(self) -> Iterator[Tree]: """ Recursively iterate through the children of the current node """ for _, child_node in self.children.items(): yield child_node if child_node.otype == DIRECTORY: yield from child_node.iterate() - def __iterNodesAttr(self) -> Iterator[Dict[str, Dict[str, Any]]]: + def _iter_nodes_attr(self) -> Iterator[Dict[str, Dict[str, Any]]]: """ Recursively iterate through the children of the current node returning an iterable of the children nodes attributes Yields: a dictionary containing a path with its known/unknown status and the SWHID """ for child_node in self.iterate(): yield child_node.attributes if child_node.otype == DIRECTORY: - yield from child_node.__iterNodesAttr() + yield from child_node._iter_nodes_attr() - def getFilesFromDir(self, dir_path: Path) -> List: + def get_files_from_dir(self, dir_path: Path) -> List: """ Retrieve files information about a specific directory path Returns: A list containing the files attributes present inside the directory given in input """ - def getFiles(node): + def get_files(node): files = [] for _, node in node.children.items(): if node.otype == CONTENT: files.append(node.attributes) return files if dir_path == self.path: - return getFiles(self) + return get_files(self) else: for node in self.iterate(): if node.path == dir_path: - return getFiles(node) + return get_files(node) raise InvalidDirectoryPath( "The directory provided doesn't match any stored directory" ) - def __getSubDirsInfo(self, root, directories): + def _get_sub_dirs_info(self, root, directories): """Fills the directories given in input with the contents information stored inside the directory child, only if they have contents. """ for path, child_node in self.children.items(): if child_node.otype == DIRECTORY: rel_path = path.relative_to(root) contents_info = child_node.count_contents() # checks the first element of the tuple # (the number of contents in a directory) # if it is equal to zero it means that there are no contents # in that directory. if not contents_info[0] == 0: directories[rel_path] = contents_info if child_node.has_dirs(): - child_node.__getSubDirsInfo(root, directories) + child_node._get_sub_dirs_info(root, directories) - def getDirectoriesInfo(self, root: Path) -> Dict[Path, Tuple[int, int]]: + def get_directories_info(self, root: Path) -> Dict[Path, Tuple[int, int]]: """Get information about all directories under the given root. Returns: A dictionary with a directory path as key and the relative contents information (the result of count_contents) as values. """ directories = {root: self.count_contents()} - self.__getSubDirsInfo(root, directories) + self._get_sub_dirs_info(root, directories) return directories def count_contents(self) -> Tuple[int, int]: """Count how many contents are present inside a directory. If a directory has a SWHID returns as it has all the contents. Returns: A tuple with the total number of the contents and the number of contents known (the ones that have a persistent identifier). """ contents = 0 discovered = 0 if not self.otype == DIRECTORY: raise InvalidObjectType( - "Can't calculate contents of the " "object type: %s" % self.otype + "Can't count contents of the object type: %s" % self.otype ) if self.known: # to identify a directory with all files/directories present return (1, 1) else: for _, child_node in self.children.items(): if child_node.otype == CONTENT: contents += 1 if child_node.known: discovered += 1 return (contents, discovered) def has_dirs(self) -> bool: """Checks if node has directories """ for _, child_node in self.children.items(): if child_node.otype == DIRECTORY: return True return False diff --git a/swh/scanner/scanner.py b/swh/scanner/scanner.py index 10a56c3..246b2ff 100644 --- a/swh/scanner/scanner.py +++ b/swh/scanner/scanner.py @@ -1,245 +1,245 @@ # Copyright (C) 2020 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information import asyncio import fnmatch import glob import itertools import os from pathlib import Path import re from typing import Any, Dict, Iterable, Iterator, List, Pattern, Tuple, Union import aiohttp from swh.model.from_disk import Content, Directory, accept_all_directories from swh.model.identifiers import CONTENT, DIRECTORY, parse_swhid, swhid from .dashboard.dashboard import run_app from .exceptions import InvalidDirectoryPath, error_response from .model import Tree from .plot import generate_sunburst async def swhids_discovery( swhids: List[str], session: aiohttp.ClientSession, api_url: str, ) -> Dict[str, Dict[str, bool]]: """API Request to get information about the SoftWare Heritage persistent IDentifiers (SWHIDs) given in input. Args: swhids: a list of SWHIDS api_url: url for the API request Returns: A dictionary with: key: SWHID searched value: value['known'] = True if the SWHID is found value['known'] = False if the SWHID is not found """ endpoint = api_url + "known/" chunk_size = 1000 requests = [] def get_chunk(swhids): for i in range(0, len(swhids), chunk_size): yield swhids[i : i + chunk_size] async def make_request(swhids): async with session.post(endpoint, json=swhids) as resp: if resp.status != 200: error_response(resp.reason, resp.status, endpoint) return await resp.json() if len(swhids) > chunk_size: for swhids_chunk in get_chunk(swhids): requests.append(asyncio.create_task(make_request(swhids_chunk))) res = await asyncio.gather(*requests) # concatenate list of dictionaries return dict(itertools.chain.from_iterable(e.items() for e in res)) else: return await make_request(swhids) def directory_filter( path_name: Union[str, bytes], exclude_patterns: Iterable[Pattern[str]] ) -> bool: """It checks if the path_name is matching with the patterns given in input. It is also used as a `dir_filter` function when generating the directory object from `swh.model.from_disk` Returns: False if the directory has to be ignored, True otherwise """ path = Path(path_name.decode() if isinstance(path_name, bytes) else path_name) for sre_pattern in exclude_patterns: if sre_pattern.match(str(path)): return False return True def get_subpaths( path: Path, exclude_patterns: Iterable[Pattern[str]] ) -> Iterator[Tuple[Path, str]]: """Find the SoftWare Heritage persistent IDentifier (SWHID) of the directories and files under a given path. Args: path: the root path Yields: pairs of: path, the relative SWHID """ def swhid_of(path): if path.is_dir(): if exclude_patterns: def dir_filter(dirpath, *args): return directory_filter(dirpath, exclude_patterns) else: dir_filter = accept_all_directories obj = Directory.from_disk( path=bytes(path), dir_filter=dir_filter ).get_data() return swhid(DIRECTORY, obj) else: obj = Content.from_file(path=bytes(path)).get_data() return swhid(CONTENT, obj) dirpath, dnames, fnames = next(os.walk(path)) for node in itertools.chain(dnames, fnames): sub_path = Path(dirpath).joinpath(node) yield (sub_path, swhid_of(sub_path)) async def parse_path( path: Path, session: aiohttp.ClientSession, api_url: str, exclude_patterns: Iterable[Pattern[str]], ) -> Iterator[Tuple[str, str, bool]]: """Check if the sub paths of the given path are present in the archive or not. Args: path: the source path api_url: url for the API request Returns: a map containing tuples with: a subpath of the given path, the SWHID of the subpath and the result of the api call """ parsed_paths = dict(get_subpaths(path, exclude_patterns)) parsed_swhids = await swhids_discovery( list(parsed_paths.values()), session, api_url ) def unpack(tup): subpath, swhid = tup return (subpath, swhid, parsed_swhids[swhid]["known"]) return map(unpack, parsed_paths.items()) async def run( config: Dict[str, Any], root: str, source_tree: Tree, exclude_patterns: Iterable[Pattern[str]], ) -> None: """Start scanning from the given root. It fills the source tree with the path discovered. Args: root: the root path to scan api_url: url for the API request """ api_url = config["web-api"]["url"] async def _scan(root, session, api_url, source_tree, exclude_patterns): for path, obj_swhid, known in await parse_path( root, session, api_url, exclude_patterns ): obj_type = parse_swhid(obj_swhid).object_type if obj_type == CONTENT: - source_tree.addNode(path, obj_swhid, known) + source_tree.add_node(path, obj_swhid, known) elif obj_type == DIRECTORY and directory_filter(path, exclude_patterns): - source_tree.addNode(path, obj_swhid, known) + source_tree.add_node(path, obj_swhid, known) if not known: await _scan(path, session, api_url, source_tree, exclude_patterns) if config["web-api"]["auth-token"]: headers = {"Authorization": f"Bearer {config['web-api']['auth-token']}"} else: headers = {} async with aiohttp.ClientSession(headers=headers) as session: await _scan(root, session, api_url, source_tree, exclude_patterns) def extract_regex_objs( root_path: Path, patterns: Iterable[str] ) -> Iterator[Pattern[str]]: """Generates a regex object for each pattern given in input and checks if the path is a subdirectory or relative to the root path. Yields: an SRE_Pattern object """ for pattern in patterns: for path in glob.glob(pattern): dirpath = Path(path) if root_path not in dirpath.parents: error_msg = ( f'The path "{dirpath}" is not a subdirectory or relative ' f'to the root directory path: "{root_path}"' ) raise InvalidDirectoryPath(error_msg) regex = fnmatch.translate((pattern)) yield re.compile(regex) def scan( config: Dict[str, Any], root_path: str, exclude_patterns: Iterable[str], out_fmt: str, interactive: bool, ): """Scan a source code project to discover files and directories already present in the archive""" sre_patterns = set() if exclude_patterns: sre_patterns = { reg_obj for reg_obj in extract_regex_objs(Path(root_path), exclude_patterns) } source_tree = Tree(Path(root_path)) loop = asyncio.get_event_loop() loop.run_until_complete(run(config, root_path, source_tree, sre_patterns)) if interactive: root = Path(root_path) - directories = source_tree.getDirectoriesInfo(root) + directories = source_tree.get_directories_info(root) figure = generate_sunburst(directories, root) run_app(figure, source_tree) else: source_tree.show(out_fmt) diff --git a/swh/scanner/tests/conftest.py b/swh/scanner/tests/conftest.py index ac17096..5036b13 100644 --- a/swh/scanner/tests/conftest.py +++ b/swh/scanner/tests/conftest.py @@ -1,141 +1,141 @@ # Copyright (C) 2020 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information import asyncio import os from pathlib import Path import shutil import aiohttp from aioresponses import aioresponses # type: ignore import pytest from swh.model.cli import swhid_of_dir, swhid_of_file from swh.scanner.model import Tree from .flask_api import create_app @pytest.fixture def mock_aioresponse(): with aioresponses() as m: yield m @pytest.fixture def event_loop(): """Fixture that generate an asyncio event loop.""" loop = asyncio.new_event_loop() asyncio.set_event_loop(loop) yield loop loop.close() @pytest.fixture async def aiosession(): """Fixture that generate an aiohttp Client Session.""" session = aiohttp.ClientSession() yield session session.detach() @pytest.fixture(scope="session") def temp_folder(tmp_path_factory): """Fixture that generates a temporary folder with the following structure: .. code-block:: python root = { subdir: { subsubdir filesample.txt filesample2.txt } subdir2 subfile.txt } """ root = tmp_path_factory.getbasetemp() subdir = tmp_path_factory.mktemp("subdir") subsubdir = subdir.joinpath("subsubdir") subsubdir.mkdir() subdir2 = tmp_path_factory.mktemp("subdir2") subfile = root / "subfile.txt" subfile.touch() filesample = subdir / "filesample.txt" filesample.touch() filesample2 = subdir / "filesample2.txt" filesample2.touch() avail_path = { subdir: swhid_of_dir(bytes(subdir)), subsubdir: swhid_of_dir(bytes(subsubdir)), subdir2: swhid_of_dir(bytes(subdir2)), subfile: swhid_of_file(bytes(subfile)), filesample: swhid_of_file(bytes(filesample)), filesample2: swhid_of_file(bytes(filesample2)), } return { "root": root, "paths": avail_path, "filesample": filesample, "filesample2": filesample2, "subsubdir": subsubdir, "subdir": subdir, } @pytest.fixture(scope="function") def example_tree(temp_folder): """Fixture that generate a Tree with the root present in the session fixture "temp_folder". """ example_tree = Tree(temp_folder["root"]) assert example_tree.path == temp_folder["root"] return example_tree @pytest.fixture(scope="function") def example_dirs(example_tree, temp_folder): """ Fixture that fill the fixture example_tree with the values contained in the fixture temp_folder and returns the directories information of the filled example_tree. """ root = temp_folder["root"] filesample_path = temp_folder["filesample"] filesample2_path = temp_folder["filesample2"] subsubdir_path = temp_folder["subsubdir"] known_paths = [filesample_path, filesample2_path, subsubdir_path] for path, swhid in temp_folder["paths"].items(): if path in known_paths: - example_tree.addNode(path, swhid, True) + example_tree.add_node(path, swhid, True) else: - example_tree.addNode(path, swhid, False) + example_tree.add_node(path, swhid, False) - return example_tree.getDirectoriesInfo(root) + return example_tree.get_directories_info(root) @pytest.fixture def test_sample_folder(datadir, tmp_path): """Location of the "data" folder """ archive_path = Path(os.path.join(datadir, "sample-folder.tgz")) assert archive_path.exists() shutil.unpack_archive(archive_path, extract_dir=tmp_path) test_sample_folder = Path(os.path.join(tmp_path, "sample-folder")) assert test_sample_folder.exists() return test_sample_folder @pytest.fixture(scope="session") def app(): """Flask backend API (used by live_server).""" app = create_app() return app diff --git a/swh/scanner/tests/test_dashboard.py b/swh/scanner/tests/test_dashboard.py index 5d70354..ab7bfd5 100644 --- a/swh/scanner/tests/test_dashboard.py +++ b/swh/scanner/tests/test_dashboard.py @@ -1,51 +1,51 @@ # Copyright (C) 2020 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information import dash_html_components as html from swh.scanner.dashboard.dashboard import generate_table_body def test_generate_table_body(example_tree, temp_folder): subdir_path = temp_folder["subdir"] for path, swhid in temp_folder["paths"].items(): - example_tree.addNode(path, swhid, True) + example_tree.add_node(path, swhid, True) generated_body = generate_table_body(subdir_path, example_tree) expected_body = [ html.Tbody( [ html.Tr( [ html.Td("✔"), html.Td( html.A( children="filesample.txt", href=f"file://{subdir_path}/filesample.txt", ) ), html.Td("swh:1:cnt:e69de29bb2d1d6434b8b29ae775ad8c2e48c5391"), ] ), html.Tr( [ html.Td("✔"), html.Td( html.A( children="filesample2.txt", href=f"file://{subdir_path}/filesample2.txt", ) ), html.Td("swh:1:cnt:e69de29bb2d1d6434b8b29ae775ad8c2e48c5391"), ] ), ] ) ] # workaround: dash_html_component.__eq__ checks for object identity only assert str(generated_body) == str(expected_body) diff --git a/swh/scanner/tests/test_model.py b/swh/scanner/tests/test_model.py index 15192d9..f089ace 100644 --- a/swh/scanner/tests/test_model.py +++ b/swh/scanner/tests/test_model.py @@ -1,108 +1,108 @@ # Copyright (C) 2020 The Software Heritage developers # See the AUTHORS file at the top-level directory of this distribution # License: GNU General Public License version 3, or any later version # See top-level LICENSE file for more information import pytest from swh.scanner.exceptions import InvalidDirectoryPath def test_tree_add_node(example_tree, temp_folder): avail_paths = temp_folder["paths"].keys() for path, swhid in temp_folder["paths"].items(): - example_tree.addNode(path, swhid, False) + example_tree.add_node(path, swhid, False) for path, node in example_tree.children.items(): assert path in avail_paths if node.children: for subpath, subnode in node.children.items(): assert subpath in avail_paths def test_to_json_no_one_present(example_tree, temp_folder): for path, swhid in temp_folder["paths"].items(): - example_tree.addNode(path, swhid, False) + example_tree.add_node(path, swhid, False) - result = example_tree.toDict() + result = example_tree.to_dict() assert len(result) == 6 for _, node_info in result.items(): assert node_info["known"] is False def test_get_json_tree_all_present(example_tree, temp_folder): for path, swhid in temp_folder["paths"].items(): - example_tree.addNode(path, swhid, True) + example_tree.add_node(path, swhid, True) - result = example_tree.toDict() + result = example_tree.to_dict() assert len(result) == 6 for _, node_info in result.items(): assert node_info["known"] is True def test_get_json_tree_only_one_present(example_tree, temp_folder): root = temp_folder["root"] filesample_path = temp_folder["filesample"] for path, swhid in temp_folder["paths"].items(): - example_tree.addNode(path, swhid, True if path == filesample_path else False) + example_tree.add_node(path, swhid, True if path == filesample_path else False) - result = example_tree.toDict() + result = example_tree.to_dict() assert len(result) == 6 for path, node_attr in result.items(): if path == str(root) + "/subdir0/filesample.txt": assert node_attr["known"] is True else: assert node_attr["known"] is False def test_get_directories_info(example_tree, temp_folder): root_path = temp_folder["root"] filesample_path = temp_folder["filesample"] filesample2_path = temp_folder["filesample2"] subdir_path = temp_folder["subdir"].relative_to(root_path) subsubdir_path = temp_folder["subsubdir"].relative_to(root_path) for path, swhid in temp_folder["paths"].items(): if path == filesample_path or path == filesample2_path: - example_tree.addNode(path, swhid, True) + example_tree.add_node(path, swhid, True) else: - example_tree.addNode(path, swhid, False) + example_tree.add_node(path, swhid, False) - directories = example_tree.getDirectoriesInfo(example_tree.path) + directories = example_tree.get_directories_info(example_tree.path) assert subsubdir_path not in directories assert directories[subdir_path] == (2, 2) def test_get_files_from_dir(example_tree, temp_folder): subdir_path = temp_folder["subdir"] for path, swhid in temp_folder["paths"].items(): - example_tree.addNode(path, swhid, True) + example_tree.add_node(path, swhid, True) - files = example_tree.getFilesFromDir(subdir_path) + files = example_tree.get_files_from_dir(subdir_path) assert len(files) == 2 def test_get_files_source_path(example_tree, temp_folder): for path, swhid in temp_folder["paths"].items(): - example_tree.addNode(path, swhid, True) + example_tree.add_node(path, swhid, True) - files = example_tree.getFilesFromDir(example_tree.path) + files = example_tree.get_files_from_dir(example_tree.path) assert len(files) == 1 def test_get_files_from_dir_raise_exception(example_tree, temp_folder): for path, swhid in temp_folder["paths"].items(): - example_tree.addNode(path, swhid, True) + example_tree.add_node(path, swhid, True) with pytest.raises(InvalidDirectoryPath): - example_tree.getFilesFromDir("test/") + example_tree.get_files_from_dir("test/")