Move extractcode API to extractcode #2233

Also move extractcli tests there

Signed-off-by: Philippe Ombredanne <pombredanne@nexb.com>

Author: pombredanne

src/extractcode/NOTICE

@@ -0,0 +1,56 @@
+Software license
+================
+
+Copyright (c) 2017 nexB Inc. and others. All rights reserved.
+http://nexb.com and https://github.com/nexB/scancode-toolkit/
+The ScanCode software is licensed under the Apache License version 2.0.
+Data generated with ScanCode require an acknowledgment.
+ScanCode is a trademark of nexB Inc.
+
+You may not use this software except in compliance with the License.
+You may obtain a copy of the License at: http://apache.org/licenses/LICENSE-2.0
+Unless required by applicable law or agreed to in writing, software distributed
+under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR
+CONDITIONS OF ANY KIND, either express or implied. See the License for the
+specific language governing permissions and limitations under the License.
+
+When you publish or redistribute any data created with ScanCode or any ScanCode
+derivative work, you must accompany this data with the following acknowledgment:
+
+  Generated with ScanCode and provided on an "AS IS" BASIS, WITHOUT WARRANTIES
+  OR CONDITIONS OF ANY KIND, either express or implied. No content created from
+  ScanCode should be considered or used as legal advice. Consult an Attorney
+  for any legal advice.
+  ScanCode is a free software code scanning tool from nexB Inc. and others.
+  Visit https://github.com/nexB/scancode-toolkit/ for support and download.
+
+
+Third-party software licenses
+=============================
+
+ScanCode embeds third-party free and open source software packages under various
+licenses including copyleft licenses. Some of the third-party software packages
+are delivered as pre-built binaries. The origin and license of these packages is
+documented by .ABOUT files.
+
+The corresponding source code for pre-compiled third-party software is available
+for immediate download from the same release page where you obtained ScanCode at:
+https://github.com/nexB/scancode-toolkit/
+or https://github.com/nexB/scancode-thirdparty-src/
+
+You may also contact us to request the source code by email at info@nexb.com or
+by postal mail at:
+
+  nexB Inc., ScanCode open source code request
+  735 Industrial Road, Suite #101, 94070 San Carlos, CA, USA
+
+Please indicate in your communication the ScanCode version for which you are
+requesting source code.
+
+
+License for ScanCode datasets
+=============================
+
+ScanCode includes datasets (e.g. for license detection) that are dedicated
+to the Public Domain using the Creative Commons CC0 1.0 Universal (CC0 1.0)
+Public Domain Dedication: http://creativecommons.org/publicdomain/zero/1.0/

src/extractcode/api.py

@@ -0,0 +1,54 @@
+#
+# Copyright (c) nexB Inc. and others. All rights reserved.
+# http://nexb.com and https://github.com/nexB/scancode-toolkit/
+# The ScanCode software is licensed under the Apache License version 2.0.
+# Data generated with ScanCode require an acknowledgment.
+# ScanCode is a trademark of nexB Inc.
+#
+# You may not use this software except in compliance with the License.
+# You may obtain a copy of the License at: http://apache.org/licenses/LICENSE-2.0
+# Unless required by applicable law or agreed to in writing, software distributed
+# under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR
+# CONDITIONS OF ANY KIND, either express or implied. See the License for the
+# specific language governing permissions and limitations under the License.
+#
+# When you publish or redistribute any data created with ScanCode or any ScanCode
+# derivative work, you must accompany this data with the following acknowledgment:
+#
+#  Generated with ScanCode and provided on an "AS IS" BASIS, WITHOUT WARRANTIES
+#  OR CONDITIONS OF ANY KIND, either express or implied. No content created from
+#  ScanCode should be considered or used as legal advice. Consult an Attorney
+#  for any legal advice.
+#  ScanCode is a free software code scanning tool from nexB Inc. and others.
+#  Visit https://github.com/nexB/scancode-toolkit/ for support and download.
+
+from __future__ import absolute_import
+from __future__ import division
+from __future__ import print_function
+from __future__ import unicode_literals
+
+
+"""
+Note: this API is unstable and still evolving.
+"""
+
+
+def extract_archives(location, recurse=True, replace_originals=False, ignore_pattern=()):
+    """
+    Yield ExtractEvent while extracting archive(s) and compressed files at
+    `location`. If `recurse` is True, extract nested archives-in-archives
+    recursively.
+    Archives and compressed files are extracted in a directory named
+    "<file_name>-extract" created in the same directory as the archive.
+    Note: this API is returning an iterable and NOT a sequence.
+    """
+    from extractcode.extract import extract
+    from extractcode import default_kinds
+    for xevent in extract(
+        location=location,
+        kinds=default_kinds,
+        recurse=recurse,
+        replace_originals=replace_originals,
+        ignore_pattern=ignore_pattern
+    ):
+        yield xevent

src/extractcode/cli.py

@@ -27,20 +27,21 @@
 from __future__ import unicode_literals
 
 from functools import partial
-import os
+from os import path
 
 import click
 click.disable_unicode_literals_warning = True
 
+from commoncode import cliutils
 from commoncode import compat
 from commoncode import fileutils
 from commoncode import filetype
 from commoncode.text import toascii
 
-from scancode_config import __version__
-from scancode.api import extract_archives
-from scancode import print_about
-from commoncode import cliutils
+from extractcode.api import extract_archives
+
+
+__version__ = '2020.09.21'
 
 
 echo_stderr = partial(click.secho, err=True)
@@ -49,7 +50,37 @@
 def print_version(ctx, param, value):
     if not value or ctx.resilient_parsing:
         return
-    echo_stderr('ScanCode extractcode version ' + __version__)
+    echo_stderr('ExtractCode version ' + __version__)
+    ctx.exit()
+
+info_text = '''
+ExtractCode is a mostly universal archive and compressed files extractor, with 
+a particular focus on code archives.
+Visit https://github.com/nexB/scancode-toolkit/ for support and download.
+
+'''
+
+notice_path = path.join(path.abspath(path.dirname(__file__)), 'NOTICE')
+notice_text = open(notice_path).read()
+
+delimiter = '\n\n\n'
+[notice_text, extra_notice_text] = notice_text.split(delimiter, 1)
+extra_notice_text = delimiter + extra_notice_text
+
+delimiter = '\n\n  '
+[notice_text, acknowledgment_text] = notice_text.split(delimiter, 1)
+acknowledgment_text = delimiter + acknowledgment_text
+
+notice = acknowledgment_text.strip().replace('  ', '')
+
+
+def print_about(ctx, param, value):
+    """
+    Click callback to print a notice.
+    """
+    if not value or ctx.resilient_parsing:
+        return
+    click.echo(info_text + notice_text + acknowledgment_text + extra_notice_text)
     ctx.exit()
 
 
@@ -93,17 +124,17 @@ class ExtractCommand(cliutils.BaseCommand):
 @click.option('--ignore', default=[], multiple=True, help='Ignore files/directories following a glob-pattern.')
 
 @click.help_option('-h', '--help')
-@click.option('--about', is_flag=True, is_eager=True, callback=print_about, help='Show information about ScanCode and licensing and exit.')
+@click.option('--about', is_flag=True, is_eager=True, callback=print_about, help='Show information about ExtractCode and licensing and exit.')
 @click.option('--version', is_flag=True, is_eager=True, callback=print_version, help='Show the version and exit.')
 def extractcode(ctx, input, verbose, quiet, shallow, replace_originals, ignore, *args, **kwargs):  # NOQA
     """extract archives and compressed files found in the <input> file or directory tree.
 
-    Use this command before scanning proper as an <input> preparation step.
     Archives found inside an extracted archive are extracted recursively.
-    Extraction is done in-place in a directory named '-extract' side-by-side with an archive.
+    Extraction for each archive is done in-place in a new directory named 
+    '<archive file name>-extract' created side-by-side with an archive.
     """
 
-    abs_location = fileutils.as_posixpath(os.path.abspath(os.path.expanduser(input)))
+    abs_location = fileutils.as_posixpath(path.abspath(path.expanduser(input)))
 
     def extract_event(item):
         """