Packagedcode to handle .podspec file

src/packagedcode/__init__.py

@@ -25,16 +25,17 @@
 from __future__ import absolute_import
 from __future__ import unicode_literals
 
-from packagedcode import build
-from packagedcode import chef
-from packagedcode import models
 from packagedcode import about
 from packagedcode import bower
-from packagedcode import conda
+from packagedcode import build
 from packagedcode import cargo
+from packagedcode import chef
+from packagedcode import cocoapods
+from packagedcode import conda
 from packagedcode import freebsd
 from packagedcode import haxe
 from packagedcode import maven
+from packagedcode import models
 from packagedcode import npm
 from packagedcode import nuget
 from packagedcode import phpcomposer
@@ -62,6 +63,7 @@
     phpcomposer.PHPComposerPackage,
     haxe.HaxePackage,
     cargo.RustCargoCrate,
+    cocoapods.CocoapodsPackage,
     models.MeteorPackage,
     bower.BowerPackage,
     freebsd.FreeBSDPackage,

src/packagedcode/cocoapods.py

@@ -0,0 +1,183 @@
+# 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 print_function
+from __future__ import unicode_literals
+
+import logging
+import re
+
+import attr
+from packageurl import PackageURL
+
+from commoncode.fileutils import py2
+from commoncode import filetype
+from commoncode import fileutils
+from packagedcode import models
+from packagedcode import spec
+
+
+"""
+Handle cocoapods packages manifests for macOS and iOS
+including .podspec, Podfile and Podfile.lock files.
+See https://cocoapods.org
+"""
+
+# TODO: implementation to get dependency data using gemsfileparser
+# Check: https://gitlab.com/balasankarc/gemfileparser
+# TODO: override the license detection to detect declared_license correctly.
+
+
+TRACE = False
+
+logger = logging.getLogger(__name__)
+
+if TRACE:
+    import sys
+    logging.basicConfig(stream=sys.stdout)
+    logger.setLevel(logging.DEBUG)
+
+
+@attr.s()
+class CocoapodsPackage(models.Package):
+    metafiles = ('*.podspec',)
+    extensions = ('.podspec',)
+    default_type = 'pods'
+    default_primary_language = 'Objective-C'
+    default_web_baseurl = 'https://cocoapods.org'
+    default_download_baseurl = None
+    default_api_baseurl = None
+
+    @classmethod
+    def recognize(cls, location):
+        yield parse(location)
+
+    def repository_homepage_url(self, baseurl=default_web_baseurl):
+        return '{}/pods/{}'.format(baseurl, self.name)
+
+    def repository_download_url(self):
+        return '{}/archive/{}.zip'.format(self.homepage_url, self.version)
+
+
+def is_podspec(location):
+    """
+    Checks is the file is a podspec file or not.
+    """
+    return (filetype.is_file(location) and location.endswith('.podspec'))
+
+
+def parse(location):
+    """
+    Return a Package object from a .podspec file or None.
+    """
+    if not is_podspec(location):
+        return
+
+    podspec_data = spec.parse_spec(location)
+    return build_package(podspec_data)
+
+
+def build_package(podspec_data):
+    """
+    Return a Pacakge object from a package data mapping or None.
+    """
+    name = podspec_data.get('name')
+    version = podspec_data.get('version')
+    declared_license = podspec_data.get('license')
+    summary = podspec_data.get('summary')
+    description = podspec_data.get('description')
+    homepage_url = podspec_data.get('homepage_url')
+    source = podspec_data.get('source')
+    authors = podspec_data.get('author') or None
+
+    author_names = []
+    author_email = []
+    if authors:
+        for split_author in authors:
+            split_author = split_author.strip()
+            author, email = parse_person(split_author)
+            author_names.append(author)
+            author_email.append(email)
+
+    parties = []
+    if authors:
+        parties.append(
+            models.Party(
+                type=models.party_person,
+                name=', '.join(author_names),
+                email=', '.join(author_email),
+                role='author'
+            )
+        )
+
+    if len(summary) > len(description):
+        description = summary
+
+    package = CocoapodsPackage(
+        name=name,
+        version=version,
+        vcs_url=source,
+        source_packages=list(source.split('\n')),
+        description=description,
+        declared_license=declared_license,
+        homepage_url=homepage_url,
+        parties=parties
+    )
+    return package
+
+
+person_parser = re.compile(
+    r'^(?P<name>[\w\s(),-_.,]+)'
+    r'=>'
+    r'(?P<email>[\S+]+$)'
+).match
+
+person_parser_only_name = re.compile(
+    r'^(?P<name>[\w\s(),-_.,]+)'
+).match
+
+
+def parse_person(person):
+    """
+    https://guides.cocoapods.org/syntax/podspec.html#authors
+    Author can be in the form:
+        s.author = 'Rohit Potter'
+        or
+        s.author = 'Rohit Potter=>rohit@gmail.com'
+    Author check:
+    >>> p = parse_person('Rohit Potter=>rohit@gmail.com')
+    >>> assert p == ('Rohit Potter', 'rohit@gmail.com')
+    >>> p = parse_person('Rohit Potter')
+    >>> assert p == ('Rohit Potter', None)
+    """
+    parsed = person_parser(person)
+    if not parsed:
+        parsed = person_parser_only_name(person)
+        name = parsed.group('name')
+        email = None
+    else:
+        name = parsed.group('name')
+        email = parsed.group('email')
+
+    return name, email

src/packagedcode/spec.py

@@ -0,0 +1,118 @@
+# 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.
+
+
+import csv
+import glob
+import io
+import os
+import re
+
+
+"""
+Handle Cocoapods(.podspec) and Ruby(.gemspec) files.
+"""
+
+
+def get_stripped_data(line):
+    """
+    Return data after removing unnecessary special character and space.
+    """
+    if '#' in line:
+        line = line[:line.index('#')]
+    stripped_data = line.strip()
+    stripped_data = stripped_data.replace("'", '')
+    stripped_data = stripped_data.replace('"', '')
+    stripped_data = stripped_data.replace('{', '')
+    stripped_data = stripped_data.replace('}', '')
+    stripped_data = stripped_data.strip()
+    return stripped_data
+
+
+def get_description(location):
+    """
+    https://guides.cocoapods.org/syntax/podspec.html#description
+    description is in the form:
+    spec.description = <<-DESC
+                     Computes the meaning of life.
+                     Features:
+                     1. Is self aware
+                     ...
+                     42. Likes candies.
+                    DESC
+    Return description from podspec.
+    """
+    with io.open(location, encoding='utf-8', closefd=True) as data:
+        lines = data.readlines()
+    description = ''
+    for i, content in enumerate(lines):
+        if '.description' in content:
+            for cont in lines[i+1:]:
+                if 'DESC' in cont:
+                    break
+                description += ' '.join([description, cont.strip()])
+            break
+    description.strip()
+    return description
+
+
+def parse_spec(location):
+    """
+    Return dictionary contains podspec or gemspec file data.
+    """
+    with io.open(location, encoding='utf-8', closefd=True) as data:
+        lines = data.readlines()
+
+    spec_data = {}
+
+    for line in lines:
+        if '.name' in line:
+            name = re.sub(r'/*.*name.*?=', '', line)
+            spec_data['name'] = get_stripped_data(name)
+        elif '.version' in line and '.version.' not in line:
+            version = re.sub(r'/*.*version.*?=', '', line)
+            spec_data['version'] = get_stripped_data(version)
+        elif '.license' in line:
+            license_type = re.sub(r'/*.*license.*?=', '', line)
+            spec_data['license'] = get_stripped_data(license_type)
+        elif '.source' in line and '.source_files' not in line:
+            source = re.sub(r'/*.*source.*?>', '', line)
+            stripped_source = re.sub(r',.*', '', source)
+            spec_data['source'] = get_stripped_data(stripped_source)
+        elif '.author' in line:
+            authors = re.sub(r'/*.*author.*?=', '', line)
+            stripped_authors = get_stripped_data(authors)
+            stripped_authors = stripped_authors.replace(' => ', "=>")
+            stripped_authors = stripped_authors.strip()
+            stripped_authors = stripped_authors.split(',')
+            spec_data['author'] = stripped_authors
+        elif '.summary' in line:
+            summary = re.sub(r'/*.*summary.*?=', '', line)
+            spec_data['summary'] = get_stripped_data(summary)
+        elif '.description' in line:
+            spec_data['description'] = get_description(location)
+        elif '.homepage' in line:
+            homepage_url = re.sub(r'/*.*homepage.*?=', '', line)
+            spec_data['homepage_url'] = get_stripped_data(homepage_url)
+
+    return spec_data

tests/packagedcode/data/plugin/help.txt

@@ -200,6 +200,12 @@ Package: nuget
   extensions: .nupkg
   filetypes: zip archive, microsoft ooxml
 
+--------------------------------------------
+Package: pods
+  class: packagedcode.cocoapods:CocoapodsPackage
+  metafiles: *.podspec
+  extensions: .podspec
+
 --------------------------------------------
 Package: pypi
   class: packagedcode.pypi:PythonPackage