fosslight-source 2.2.2__tar.gz → 2.2.4__tar.gz

{fosslight_source-2.2.2/src/fosslight_source.egg-info → fosslight_source-2.2.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: fosslight_source
-Version: 2.2.2
+Version: 2.2.4
 Summary: FOSSLight Source Scanner
 Home-page: https://github.com/fosslight/fosslight_source_scanner
 Download-URL: https://github.com/fosslight/fosslight_source_scanner
@@ -17,7 +17,7 @@ License-File: LICENSE
 Requires-Dist: pyparsing
 Requires-Dist: scanoss>=1.18.0
 Requires-Dist: XlsxWriter
-Requires-Dist: fosslight_util>=2.1.34
+Requires-Dist: fosslight_util>=2.1.37
 Requires-Dist: PyYAML
 Requires-Dist: wheel>=0.38.1
 Requires-Dist: intbitset

{fosslight_source-2.2.2 → fosslight_source-2.2.4}/requirements.txt

@@ -1,7 +1,7 @@
 pyparsing
 scanoss>=1.18.0
 XlsxWriter
-fosslight_util>=2.1.34
+fosslight_util>=2.1.37
 PyYAML
 wheel>=0.38.1
 intbitset

{fosslight_source-2.2.2 → fosslight_source-2.2.4}/setup.py

@@ -14,7 +14,7 @@ with open('requirements.txt', 'r', 'utf-8') as f:
 if __name__ == "__main__":
     setup(
         name='fosslight_source',
-        version='2.2.2',
+        version='2.2.4',
         package_dir={"": "src"},
         packages=find_packages(where='src'),
         description='FOSSLight Source Scanner',

fosslight_source-2.2.4/src/fosslight_source/_help.py

@@ -0,0 +1,67 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+# Copyright (c) 2021 LG Electronics Inc.
+# SPDX-License-Identifier: Apache-2.0
+from fosslight_util.help import PrintHelpMsg, print_package_version
+from fosslight_util.output_format import SUPPORT_FORMAT
+
+_HELP_MESSAGE_SOURCE_SCANNER = f"""
+    📖 Usage
+    ────────────────────────────────────────────────────────────────────
+    fosslight_source [options] <arguments>
+
+    📝 Description
+    ────────────────────────────────────────────────────────────────────
+    FOSSLight Source Scanner analyzes source code to detect copyright and
+    license information using several modes.
+
+    Note: Build scripts, binary files, and test directories are automatically
+          excluded from analysis.
+
+    📚 Guide: https://fosslight.org/fosslight-guide/scanner/2_source.html
+
+    ⚙️  General Options
+    ────────────────────────────────────────────────────────────────────
+    -p <path>              Source path to analyze (default: current directory)
+    -o <path>              Output file path or directory
+    -f <format>            Output formats: {', '.join(SUPPORT_FORMAT)}
+                           (multiple formats can be specified, separated by space)
+    -e <pattern>           Exclude paths from analysis (files and directories)
+                           ⚠️  IMPORTANT: Always wrap in quotes to avoid shell expansion
+                           Example: fosslight_source -e "dev/" "tests/" "*.jar"
+    -m                     Generate detailed scan results on separate sheets
+    -h                     Show this help message
+    -v                     Show version information
+
+    🔍 Scanner-Specific Options
+    ────────────────────────────────────────────────────────────────────
+    -s <mode>              Choose mode: scancode, scanoss, kb, or all(default)
+    -c <number>            Number of CPU cores/threads to use for scanning
+    -t <seconds>           Timeout in seconds for ScanCode scanning
+    -j                     Generate raw scanner results in JSON format
+    --no_correction        Skip OSS information correction with sbom-info.yaml
+    --correct_fpath <path> Path to custom sbom-info.yaml file
+
+    💡 Examples
+    ────────────────────────────────────────────────────────────────────
+    # Scan current directory
+    fosslight_source
+
+    # Scan specific path with exclusions
+    fosslight_source -p /path/to/source -e "test/" "node_modules/"
+
+    # Generate output in specific format
+    fosslight_source -f excel -o results/
+
+    # Generate raw scanner results in JSON format
+    fosslight_source -p /path/to/source -j
+"""
+
+
+def print_version(pkg_name: str) -> None:
+    print_package_version(pkg_name, "FOSSLight Source Scanner Version:")
+
+
+def print_help_msg_source_scanner() -> None:
+    helpMsg = PrintHelpMsg(_HELP_MESSAGE_SOURCE_SCANNER)
+    helpMsg.print_help_msg(True)

{fosslight_source-2.2.2 → fosslight_source-2.2.4}/src/fosslight_source/cli.py

@@ -30,6 +30,7 @@ from ._scan_item import SourceItem, KB_URL
 from fosslight_util.oss_item import ScannerItem
 from typing import Tuple
 from ._scan_item import is_manifest_file
+import shutil
 
 
 SRC_SHEET_NAME = 'SRC_FL_Source'
@@ -40,9 +41,7 @@ MERGED_HEADER = {SRC_SHEET_NAME: ['ID', 'Source Path', 'OSS Name',
                                   'OSS Version', 'License', 'Download Location',
                                   'Homepage', 'Copyright Text', 'Exclude', 'Comment', 'license_reference']}
 SCANNER_TYPE = ['kb', 'scancode', 'scanoss', 'all']
-EXCLUDE_FILENAME = ["changelog", "config.guess", "config.sub", "changes", "ltmain.sh",
-                    "configure", "configure.ac", "depcomp", "compile", "missing", "Makefile"]
-EXCLUDE_FILE_EXTENSION = [".m4", ".in", ".po"]
+
 
 logger = logging.getLogger(constant.LOGGER_NAME)
 warnings.filterwarnings("ignore", category=FutureWarning)
@@ -138,7 +137,7 @@ def create_report_file(
     output_path: str = "", output_files: list = [],
     output_extensions: list = [], correct_mode: bool = True,
     correct_filepath: str = "", path_to_scan: str = "", path_to_exclude: list = [],
-    formats: list = [], api_limit_exceed: bool = False, files_count: int = 0
+    formats: list = [], api_limit_exceed: bool = False, files_count: int = 0, final_output_path: str = ""
 ) -> 'ScannerItem':
     """
     Create report files for given scanned result.
@@ -152,10 +151,7 @@ def create_report_file(
     sheet_list = {}
     _json_ext = ".json"
 
-    if output_path == "":
-        output_path = os.getcwd()
-    else:
-        output_path = os.path.abspath(output_path)
+    output_path = os.path.abspath(output_path)
 
     if not output_files:
         # If -o does not contains file name, set default name
@@ -199,15 +195,27 @@ def create_report_file(
     scan_item.set_cover_pathinfo(path_to_scan, path_to_exclude)
     scan_item.set_cover_comment(f"Scanned files: {files_count}")
 
-    if api_limit_exceed:
-        scan_item.set_cover_comment("(Some of) SCANOSS scan was skipped. (API limits being exceeded)")
-
-    if not merged_result:
+    if merged_result:
+        scan_item.set_cover_comment(f"Detected source : {len(merged_result)}")
+    else:
         if files_count < 1:
             scan_item.set_cover_comment("(No file detected.)")
         else:
             scan_item.set_cover_comment("(No OSS detected.)")
 
+    if api_limit_exceed:
+        scan_item.set_cover_comment("SCANOSS skipped (API limits)")
+
+    run_kb = True if selected_scanner in ['kb', 'all'] else False
+    if run_kb:
+        scan_item.set_cover_comment("KB Enabled" if check_kb_server_reachable() else "KB Unreachable")
+    display_mode = selected_scanner
+    if selected_scanner == "kb":
+        display_mode += ", scancode"
+    elif selected_scanner == "all":
+        display_mode = "kb, scancode, scanoss"
+    scan_item.set_cover_comment(f"Mode : {display_mode}")
+
     if merged_result:
         sheet_list = {}
         scan_item.append_file_items(merged_result, PKG_NAME)
@@ -243,12 +251,13 @@ def create_report_file(
         #     del sheet_list["scanoss_reference"]
         results.append(write_output_file(combined_path_and_file, output_extension, scan_item, extended_header, "", output_format))
     for success, msg, result_file in results:
+        final_result_file = result_file.replace(output_path, final_output_path)
         if success:
-            logger.info(f"Output file: {result_file}")
+            logger.info(f"Output file: {final_result_file}")
             for row in scan_item.get_cover_comment():
                 logger.info(row)
         else:
-            logger.error(f"Fail to generate result file {result_file}. msg:({msg})")
+            logger.error(f"Fail to generate result file {final_result_file}. msg:({msg})")
     return scan_item
 
 
@@ -326,7 +335,8 @@ def run_scanners(
     called_by_cli: bool = True, print_matched_text: bool = False,
     formats: list = [], time_out: int = 120,
     correct_mode: bool = True, correct_filepath: str = "",
-    selected_scanner: str = 'all', path_to_exclude: list = []
+    selected_scanner: str = 'all', path_to_exclude: list = [],
+    all_exclude_mode: tuple = ()
 ) -> Tuple[bool, str, 'ScannerItem', list, list]:
     """
     Run Scancode and scanoss.py for the given path.
@@ -357,6 +367,11 @@ def run_scanners(
 
     success, msg, output_path, output_files, output_extensions, formats = check_output_formats_v2(output_file_name, formats)
 
+    if output_path == "":
+        output_path = os.getcwd()
+    final_output_path = output_path
+    output_path = os.path.join(os.path.dirname(output_path), f'.fosslight_temp_{start_time}')
+
     logger, result_log = init_log(os.path.join(output_path, f"fosslight_log_src_{start_time}.txt"),
                                   True, logging.INFO, logging.DEBUG, PKG_NAME, path_to_scan, path_to_exclude)
 
@@ -365,10 +380,18 @@ def run_scanners(
         print_matched_text = False
 
     if success:
-        path_to_exclude_with_filename = path_to_exclude + EXCLUDE_FILENAME
-        excluded_path_with_default_exclusion, excluded_path_without_dot, excluded_files, cnt_file_except_skipped = (
-            get_excluded_paths(path_to_scan, path_to_exclude_with_filename, EXCLUDE_FILE_EXTENSION))
-        logger.debug(f"Skipped paths: {excluded_path_with_default_exclusion}")
+        if all_exclude_mode and len(all_exclude_mode) == 4:
+            (excluded_path_with_default_exclusion,
+             excluded_path_without_dot,
+             excluded_files,
+             cnt_file_except_skipped) = all_exclude_mode
+        else:
+            path_to_exclude_with_filename = path_to_exclude
+            (excluded_path_with_default_exclusion,
+             excluded_path_without_dot,
+             excluded_files,
+             cnt_file_except_skipped) = get_excluded_paths(path_to_scan, path_to_exclude_with_filename)
+            logger.debug(f"Skipped paths: {excluded_path_with_default_exclusion}")
 
         if not selected_scanner:
             selected_scanner = 'all'
@@ -381,8 +404,10 @@ def run_scanners(
                                                                                       excluded_files)
         excluded_files = set(excluded_files) if excluded_files else set()
         if selected_scanner in ['scanoss', 'all']:
-            scanoss_result, api_limit_exceed = run_scanoss_py(path_to_scan, output_file_name, formats, True, write_json_file,
-                                                              num_cores, excluded_path_with_default_exclusion, excluded_files)
+            scanoss_result, api_limit_exceed = run_scanoss_py(path_to_scan, output_path, formats, True, num_cores,
+                                                              excluded_path_with_default_exclusion, excluded_files,
+                                                              write_json_file)
+
         if selected_scanner in SCANNER_TYPE:
             run_kb = True if selected_scanner in ['kb', 'all'] else False
             spdx_downloads, manifest_licenses = metadata_collector(path_to_scan, excluded_files)
@@ -391,7 +416,7 @@ def run_scanners(
             scan_item = create_report_file(start_time, merged_result, license_list, scanoss_result, selected_scanner,
                                            print_matched_text, output_path, output_files, output_extensions, correct_mode,
                                            correct_filepath, path_to_scan, excluded_path_without_dot, formats,
-                                           api_limit_exceed, cnt_file_except_skipped)
+                                           api_limit_exceed, cnt_file_except_skipped, final_output_path)
         else:
             print_help_msg_source_scanner()
             result_log[RESULT_KEY] = "Unsupported scanner"
@@ -399,6 +424,13 @@ def run_scanners(
     else:
         result_log[RESULT_KEY] = f"Format error. {msg}"
         success = False
+
+    try:
+        shutil.copytree(output_path, final_output_path, dirs_exist_ok=True)
+        shutil.rmtree(output_path)
+    except Exception as ex:
+        logger.debug(f"Failed to move temp files: {ex}")
+
     return success, result_log.get(RESULT_KEY, ""), scan_item, license_list, scanoss_result
 
 

{fosslight_source-2.2.2 → fosslight_source-2.2.4}/src/fosslight_source/run_manifest_extractor.py

@@ -42,8 +42,6 @@ def get_licenses_from_package_json(file_path: str) -> list[str]:
 
     if isinstance(license_field, str):
         value = license_field.strip()
-        if value.upper() == 'UNLICENSED':
-            return []
         if value.upper().startswith('SEE LICENSE IN'):
             return []
         licenses.extend(_split_spdx_expression(value))
@@ -51,7 +49,7 @@ def get_licenses_from_package_json(file_path: str) -> list[str]:
         type_val = license_field.get('type')
         if isinstance(type_val, str):
             type_val = type_val.strip()
-            if type_val and type_val.upper() != 'UNLICENSED':
+            if type_val:
                 licenses.append(type_val)
 
     if not licenses:
@@ -60,13 +58,13 @@ def get_licenses_from_package_json(file_path: str) -> list[str]:
             for item in legacy:
                 if isinstance(item, str):
                     token = item.strip()
-                    if token and token.upper() != 'UNLICENSED':
+                    if token:
                         licenses.append(token)
                 elif isinstance(item, dict):
                     t = item.get('type')
                     if isinstance(t, str):
                         t = t.strip()
-                        if t and t.upper() != 'UNLICENSED':
+                        if t:
                             licenses.append(t)
 
     unique: list[str] = []

{fosslight_source-2.2.2 → fosslight_source-2.2.4}/src/fosslight_source/run_scanoss.py

@@ -8,14 +8,10 @@ import importlib_metadata
 import warnings
 import logging
 import json
-from datetime import datetime
+from typing import Tuple
 import fosslight_util.constant as constant
-from fosslight_util.set_log import init_log
-from fosslight_util.output_format import check_output_formats_v2  # , write_output_file
 from ._parsing_scanoss_file import parsing_scan_result  # scanoss
 from ._parsing_scanoss_file import parsing_extra_info  # scanoss
-import shutil
-from pathlib import Path
 from scanoss.scanner import Scanner, ScanType
 import io
 import contextlib
@@ -23,7 +19,6 @@ import contextlib
 logger = logging.getLogger(constant.LOGGER_NAME)
 warnings.filterwarnings("ignore", category=FutureWarning)
 _PKG_NAME = "fosslight_source"
-SCANOSS_RESULT_FILE = "scanner_output.wfp"
 SCANOSS_OUTPUT_FILE = "scanoss_raw_result.json"
 
 
@@ -31,9 +26,10 @@ def get_scanoss_extra_info(scanned_result: dict) -> list:
     return parsing_extra_info(scanned_result)
 
 
-def run_scanoss_py(path_to_scan: str, output_file_name: str = "", format: list = [],
-                   called_by_cli: bool = False, write_json_file: bool = False, num_threads: int = -1,
-                   path_to_exclude: list = [], excluded_files: set = None) -> list:
+def run_scanoss_py(path_to_scan: str, output_path: str = "", format: list = [],
+                   called_by_cli: bool = False, num_threads: int = -1,
+                   path_to_exclude: list = [], excluded_files: set = None,
+                   write_json_file: bool = False) -> Tuple[list, bool]:
     """
     Run scanoss.py for the given path.
 
@@ -44,30 +40,18 @@ def run_scanoss_py(path_to_scan: str, output_file_name: str = "", format: list =
     :param write_json_file: if requested, keep the raw files.
     :return scanoss_file_list: list of ScanItem (scanned result by files).
     """
-    success, msg, output_path, output_files, output_extensions, formats = check_output_formats_v2(output_file_name, format)
-
-    if not called_by_cli:
-        global logger
-        _start_time = datetime.now().strftime('%y%m%d_%H%M')
-        logger, _result_log = init_log(os.path.join(output_path, f"fosslight_log_src_{_start_time}.txt"),
-                                       True, logging.INFO, logging.DEBUG, _PKG_NAME, path_to_scan, path_to_exclude)
 
     scanoss_file_list = []
+    api_limit_exceed = False
     try:
         importlib_metadata.distribution("scanoss")
     except Exception as error:
         logger.warning(f"{error}. Skipping scan with scanoss.")
         logger.warning("Please install scanoss and dataclasses before run fosslight_source with scanoss option.")
-        return scanoss_file_list
-
-    if output_path == "":  # if json output with _write_json_file not used, output_path won't be needed.
-        output_path = os.getcwd()
-    else:
-        output_path = os.path.abspath(output_path)
-        if not os.path.isdir(output_path):
-            Path(output_path).mkdir(parents=True, exist_ok=True)
+        return scanoss_file_list, api_limit_exceed
+
     output_json_file = os.path.join(output_path, SCANOSS_OUTPUT_FILE)
-    if os.path.exists(output_json_file):  # remove scanner_output.wfp file if exist
+    if os.path.exists(output_json_file):
         os.remove(output_json_file)
 
     try:
@@ -84,7 +68,6 @@ def run_scanoss_py(path_to_scan: str, output_file_name: str = "", format: list =
             scanner.scan_folder_with_options(scan_dir=path_to_scan)
         captured_output = output_buffer.getvalue()
         api_limit_exceed = "due to service limits being exceeded" in captured_output
-        logger.debug(f"{captured_output}")
 
         if os.path.isfile(output_json_file):
             with open(output_json_file, "r") as st_json:
@@ -98,18 +81,13 @@ def run_scanoss_py(path_to_scan: str, output_file_name: str = "", format: list =
                 st_python = json.load(st_json)
                 scanoss_file_list = parsing_scan_result(st_python, excluded_files)
 
+        if not write_json_file:
+            if os.path.isfile(output_json_file):
+                os.remove(output_json_file)
+
     except Exception as error:
         logger.debug(f"SCANOSS Parsing {path_to_scan}: {error}")
 
     logger.info(f"|---Number of files detected with SCANOSS: {(len(scanoss_file_list))}")
 
-    try:
-        if write_json_file:
-            shutil.move(SCANOSS_RESULT_FILE, output_path)
-        else:
-            os.remove(output_json_file)
-            os.remove(SCANOSS_RESULT_FILE)
-    except Exception as error:
-        logger.debug(f"Moving scanoss raw files failed.: {error}")
-
     return scanoss_file_list, api_limit_exceed

{fosslight_source-2.2.2 → fosslight_source-2.2.4/src/fosslight_source.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: fosslight_source
-Version: 2.2.2
+Version: 2.2.4
 Summary: FOSSLight Source Scanner
 Home-page: https://github.com/fosslight/fosslight_source_scanner
 Download-URL: https://github.com/fosslight/fosslight_source_scanner
@@ -17,7 +17,7 @@ License-File: LICENSE
 Requires-Dist: pyparsing
 Requires-Dist: scanoss>=1.18.0
 Requires-Dist: XlsxWriter
-Requires-Dist: fosslight_util>=2.1.34
+Requires-Dist: fosslight_util>=2.1.37
 Requires-Dist: PyYAML
 Requires-Dist: wheel>=0.38.1
 Requires-Dist: intbitset

{fosslight_source-2.2.2 → fosslight_source-2.2.4}/src/fosslight_source.egg-info/requires.txt

@@ -1,7 +1,7 @@
 pyparsing
 scanoss>=1.18.0
 XlsxWriter
-fosslight_util>=2.1.34
+fosslight_util>=2.1.37
 PyYAML
 wheel>=0.38.1
 intbitset

{fosslight_source-2.2.2 → fosslight_source-2.2.4}/tests/test_tox.py

@@ -118,6 +118,8 @@ def test_help_command():
 
 
 def test_scan_command():
+    os.makedirs("test_scan", exist_ok=True)
+
     success, _ = run_command("fosslight_source -p tests/test_files -o test_scan/scan_result.csv")
     assert success is True, "Test Release: Failed to generate scan result CSV file"
 
@@ -131,6 +133,8 @@ def test_scan_command():
 
 
 def test_exclude_command():
+    os.makedirs("test_scan2", exist_ok=True)
+
     success, _ = run_command(
         "fosslight_source -p tests -e test_files/test cli_test.py -j -m -o test_scan2/scan_exclude_result.csv"
     )
@@ -146,6 +150,8 @@ def test_exclude_command():
 
 
 def test_json_command():
+    os.makedirs("test_scan3", exist_ok=True)
+
     success, _ = run_command("fosslight_source -p tests/test_files -m -j -o test_scan3/")
     assert success is True, "Test release: Failed to generate JSON files"
 

fosslight_source-2.2.2/src/fosslight_source/_help.py

@@ -1,44 +0,0 @@
-#!/usr/bin/env python
-# -*- coding: utf-8 -*-
-# Copyright (c) 2021 LG Electronics Inc.
-# SPDX-License-Identifier: Apache-2.0
-from fosslight_util.help import PrintHelpMsg, print_package_version
-from fosslight_util.output_format import SUPPORT_FORMAT
-
-_HELP_MESSAGE_SOURCE_SCANNER = f"""
-    FOSSLight Source Scanner Usage: fosslight_source [option1] <arg1> [option2] <arg2>...
-
-    FOSSLight Source Scanner uses ScanCode and SCANOSS, the source code scanners, to detect
-    the copyright and license phrases contained in the file.
-    Some files (ex- build script), binary files, directory and files in specific
-    directories (ex-test) are excluded from the result.
-
-    Options:
-        Optional
-            -p <source_path>\t   Path to analyze source (Default: current directory)
-            -h\t\t\t   Print help message
-            -v\t\t\t   Print FOSSLight Source Scanner version
-            -m\t\t\t   Print additional information for scan result on separate sheets
-            -e <path>\t\t   Path to exclude from analysis (files and directories)
-            \t\t\t   * IMPORTANT: Always wrap patterns in double quotes ("") to avoid shell expansion.
-            \t\t\t     Example) fosslight_source -e "dev/" "tests/"
-            -o <output_path>\t   Output path (Path or file name)
-            -f <format>\t\t   Output file formats
-            \t\t\t   ({', '.join(SUPPORT_FORMAT)})
-            \t\t\t   Multiple formats can be specified separated by space.
-        Options only for FOSSLight Source Scanner
-            -s <scanner>\t   Select which scanner to be run (scancode, scanoss, kb, all)
-            -j\t\t\t   Generate raw result of scanners in json format
-            -t <float>\t\t   Stop scancode scanning if scanning takes longer than a timeout in seconds.
-            -c <core>\t\t   Select the number of cores to be scanned with ScanCode or threads with SCANOSS.
-            --no_correction\t   Enter if you don't want to correct OSS information with sbom-info.yaml
-            --correct_fpath <path> Path to the sbom-info.yaml file"""
-
-
-def print_version(pkg_name: str) -> None:
-    print_package_version(pkg_name, "FOSSLight Source Scanner Version:")
-
-
-def print_help_msg_source_scanner() -> None:
-    helpMsg = PrintHelpMsg(_HELP_MESSAGE_SOURCE_SCANNER)
-    helpMsg.print_help_msg(True)