diff --git a/README.md b/README.md --- a/README.md +++ b/README.md @@ -18,6 +18,7 @@ - `swh.lister.npm` - `swh.lister.phabricator` - `swh.lister.cran` +- `swh.lister.cgit` Dependencies ------------ @@ -203,6 +204,19 @@ cran_lister() ``` +## lister-cgit + +Once configured, you can execute a cgit lister using the following instructions +in a `python3` script: + +```lang=python +import logging +from swh.lister.cgit.tasks import cgit_lister + +logging.basicConfig(level=logging.DEBUG) +cgit_lister(base_url='http://git.savannah.gnu.org/cgit/') +``` + Licensing --------- diff --git a/requirements.txt b/requirements.txt --- a/requirements.txt +++ b/requirements.txt @@ -5,3 +5,4 @@ setuptools xmltodict iso8601 +beautifulsoup4 diff --git a/swh/lister/cgit/__init__.py b/swh/lister/cgit/__init__.py new file mode 100644 diff --git a/swh/lister/cgit/lister.py b/swh/lister/cgit/lister.py new file mode 100644 --- /dev/null +++ b/swh/lister/cgit/lister.py @@ -0,0 +1,276 @@ +# Copyright (C) 2019 the Software Heritage developers +# License: GNU General Public License version 3, or any later version +# See top-level LICENSE file for more information + +import random +from bs4 import BeautifulSoup +from collections import defaultdict +import requests +from urllib.parse import urlparse + +from .models import CGitModel + +from swh.lister.core.simple_lister import SimpleLister +from swh.lister.core.lister_transports import ListerOnePageApiTransport + + +class CGitLister(ListerOnePageApiTransport, SimpleLister): + MODEL = CGitModel + LISTER_NAME = 'cgit' + PAGE = None + + def __init__(self, base_url, instance=None, override_config=None): + + self.PAGE = base_url + url = urlparse(self.PAGE) + self.url_netloc = find_netloc(url) + + if not instance: + instance = url.hostname + self.instance = instance + ListerOnePageApiTransport .__init__(self) + SimpleLister.__init__(self, override_config=override_config) + + def list_packages(self, response): + """List the actual cgit instance origins from the response. + + Find the repos in all the pages by parsing over the HTML of + the `base_url`. Find the details for all the repos and return + them in the format of list of dictionary + + """ + repos_details = [] + repos = get_repo_list(response) + soup = make_repo_soup(response) + pages = self.get_page(soup) + if len(pages) > 1: + repos.extend(self.get_all_pages(pages)) + + for repo in repos: + repo_name = repo.a.text + repo_url = self.get_url(repo) + origin_url = find_origin_url(repo_url) + + try: + time = repo.span['title'] + except Exception: + time = None + + if origin_url is not None: + repos_details.append({ + 'name': repo_name, + 'time': time, + 'origin_url': origin_url, + }) + + random.shuffle(repos_details) + return repos_details + + def get_page(self, soup): + """Find URL of all pages + + Finds URL of all the pages that are present by parsing over the HTML of + pagination present at the end of the page. + + Args: + soup: a beautifulsoup object of the html code present at base URL + + Returns: + list: URL of all the pages present for a cgit instance + + """ + pages = soup.find('div', {"class": "content"}).find_all('li') + + if not pages: + return [self.PAGE] + + return [self.get_url(page) for page in pages] + + def get_all_pages(self, pages): + """Find repos from all the pages + + Make the request for all the pages (except the first) present for a + particular cgit instance and finds the repos that are available + for each and every page. + + Args: + pages: list of urls of all the pages present for a particular cgit + instance + + Returns: + list: List of beautifulsoup object of the html code of all the repo + row present in all the pages(except first). + + """ + all_repos = [] + for page in pages[1:]: + response = requests.get(page) + repos = get_repo_list(response) + all_repos.extend(repos) + + return all_repos + + def get_url(self, repo): + """Finds url of a repo page. + + Finds the url of a repo page by parsing over the html of the row of + that repo present in the base url. + + Args: + repo: a beautifulsoup object of the html code of the repo row + present in base url. + + Returns: + string: The url of a repo. + + """ + suffix = repo.a['href'] + return self.url_netloc + suffix + + def get_model_from_repo(self, repo): + """Transform from repository representation to model. + + """ + return { + 'uid': self.PAGE + repo['name'], + 'name': repo['name'], + 'full_name': repo['name'], + 'html_url': repo['origin_url'], + 'origin_url': repo['origin_url'], + 'origin_type': 'git', + 'time_updated': repo['time'], + 'instance': self.instance, + } + + def transport_response_simplified(self, repos_details): + """Transform response to list for model manipulation. + + """ + return [self.get_model_from_repo(repo) for repo in repos_details] + + +def find_netloc(url): + """Finds the network location from then base_url + + All the url in the repo are relative to the network location part of base + url, so we need to compute it to reconstruct all the urls. + + Args: + url: urllib object of base_url + + Returns: + string: Scheme and Network location part in the base URL. + + Example: + For base_url = https://git.kernel.org/pub/scm/ + >>> find_netloc(url) + 'https://git.kernel.org' + + """ + return '%s://%s' % (url.scheme, url.netloc) + + +def get_repo_list(response): + """Find all the rows with repo for a particualar page on the base url + + Finds all the repos on page and retuens a list of all the repos. Each + element of the list is a beautifulsoup object representing a repo. + + Args: + response: server response + + Returns: + list of all the repos on a page. + + """ + repo_soup = make_repo_soup(response) + return repo_soup \ + .find('div', {"class": "content"}).find_all("tr", {"class": ""}) + + +def make_repo_soup(response): + """Makes BeautifulSoup object of the response + + """ + return BeautifulSoup(response.text, features="html.parser") + + +def find_origin_url(repo_url): + """Finds origin url for a repo. + + Finds the origin url for a particular repo by parsing over the page of + that repo. + + Args: + repo_url: URL of the repo. + + Returns: + string: Origin url for the repo. + + Examples: + + >>> find_origin_url( + 'http://git.savannah.gnu.org/cgit/fbvbconv-py.git/') + 'https://git.savannah.gnu.org/git/fbvbconv-py.git' + + """ + + response = requests.get(repo_url) + repo_soup = make_repo_soup(response) + + origin_urls = find_all_origin_url(repo_soup) + return priority_origin_url(origin_urls) + + +def find_all_origin_url(soup): + """Finds all possible origin url for a repo. + + Finds all the origin url for a particular repo by parsing over the html of + repo page. + + Args: + soup: a beautifulsoup object repo representation. + + Returns: + dictionary: All possible origin urls for a repository (dict with + key 'protocol', value the associated url). + + Examples: + If soup is beautifulsoup object of the html code at + http://git.savannah.gnu.org/cgit/fbvbconv-py.git/ + + >>> print(find_all_origin_url(soup)) + { 'https': 'https://git.savannah.gnu.org/git/fbvbconv-py.git', + 'ssh': 'ssh://git.savannah.gnu.org/srv/git/fbvbconv-py.git', + 'git': 'git://git.savannah.gnu.org/fbvbconv-py.git'} + """ + origin_urls = defaultdict(dict) + found_clone_word = False + + for i in soup.find_all('tr'): + if found_clone_word: + link = i.text + protocol = link[:link.find(':')] + origin_urls[protocol] = link + if i.text == 'Clone': + found_clone_word = True + + return origin_urls + + +def priority_origin_url(origin_url): + """Finds the highest priority link for a particular repo. + + Priority order is https>http>git>ssh. + + Args: + origin_urls (Dict): All possible origin urls for a repository + (key 'protocol', value the associated url) + + Returns: + Url (str) with the highest priority. + + """ + for protocol in ['https', 'http', 'git', 'ssh']: + if protocol in origin_url: + return origin_url[protocol] diff --git a/swh/lister/cgit/models.py b/swh/lister/cgit/models.py new file mode 100644 --- /dev/null +++ b/swh/lister/cgit/models.py @@ -0,0 +1,18 @@ +# Copyright (C) 2019 the Software Heritage developers +# License: GNU General Public License version 3, or any later version +# See top-level LICENSE file for more information + +from sqlalchemy import Column, String + +from ..core.models import ModelBase + + +class CGitModel(ModelBase): + """a CGit repository representation + + """ + __tablename__ = 'cgit_repo' + + uid = Column(String, primary_key=True) + time_updated = Column(String) + instance = Column(String, index=True) diff --git a/swh/lister/cgit/tasks.py b/swh/lister/cgit/tasks.py new file mode 100644 --- /dev/null +++ b/swh/lister/cgit/tasks.py @@ -0,0 +1,23 @@ +# Copyright (C) 2019 the Software Heritage developers +# License: GNU General Public License version 3, or any later version +# See top-level LICENSE file for more information + +from swh.scheduler.celery_backend.config import app + +from .lister import CGitLister + + +def new_lister(base_url='https://git.savannah.gnu.org/cgit/', + instance='savannah-gnu', **kw): + return CGitLister(base_url=base_url, instance=instance, **kw) + + +@app.task(name=__name__ + '.CGitListerTask') +def cgit_lister(**lister_args): + lister = new_lister(**lister_args) + lister.run() + + +@app.task(name=__name__ + '.ping') +def ping(): + return 'OK' diff --git a/swh/lister/cgit/tests/__init__.py b/swh/lister/cgit/tests/__init__.py new file mode 100644 diff --git a/swh/lister/cgit/tests/api_response.html b/swh/lister/cgit/tests/api_response.html new file mode 100644 --- /dev/null +++ b/swh/lister/cgit/tests/api_response.html @@ -0,0 +1,47 @@ + + + +fbvbconv-py.git - Unnamed repository; edit this file 'description' to name the repository. + + + + + + + + + + +
+ + + + +
+summaryrefslogtreecommitdiff
+ + + +
+
+
+ + + + + + + +
BranchCommit messageAuthorAge
masterinitial importJohannes Stezenbach2 years
 
 
AgeCommit messageAuthorFilesLines
2017-06-02initial importHEADmasterJohannes Stezenbach3-0/+889
 
Clone
git://git.savannah.gnu.org/fbvbconv-py.git
https://git.savannah.gnu.org/git/fbvbconv-py.git
ssh://git.savannah.gnu.org/srv/git/fbvbconv-py.git
+
generated by cgit v1.0-41-gc330 at 2019-06-19 10:51:46 +0000
+
+ + diff --git a/swh/lister/cgit/tests/conftest.py b/swh/lister/cgit/tests/conftest.py new file mode 100644 --- /dev/null +++ b/swh/lister/cgit/tests/conftest.py @@ -0,0 +1 @@ +from swh.lister.core.tests.conftest import * # noqa diff --git a/swh/lister/cgit/tests/test_lister.py b/swh/lister/cgit/tests/test_lister.py new file mode 100644 --- /dev/null +++ b/swh/lister/cgit/tests/test_lister.py @@ -0,0 +1,50 @@ +# Copyright (C) 2019 the Software Heritage developers +# License: GNU General Public License version 3, or any later version +# See top-level LICENSE file for more information + + +from bs4 import BeautifulSoup +from urllib.parse import urlparse + +from swh.lister.cgit.lister import priority_origin_url, find_all_origin_url +from swh.lister.cgit.lister import find_netloc + + +def test_find_all_origin_url(): + f = open('swh/lister/cgit/tests/api_response.html') + soup = BeautifulSoup(f.read(), features="html.parser") + expected_output = {'https': 'https://git.savannah.gnu.org/git/' + 'fbvbconv-py.git', + 'ssh': 'ssh://git.savannah.gnu.org/srv/git/' + 'fbvbconv-py.git', + 'git': 'git://git.savannah.gnu.org/fbvbconv-py.git'} + + output = find_all_origin_url(soup) + + for protocol, url in expected_output.items(): + assert url == output[protocol] + + +def test_priority_origin_url(): + first_input = {'https': 'https://kernel.googlesource.com/pub/scm/docs/' + 'man-pages/man-pages.git', + 'git': 'git://git.kernel.org/pub/scm/docs/man-pages/' + 'man-pages.git'} + second_input = {'git': 'git://git.savannah.gnu.org/perl-pesel.git', + 'ssh': 'ssh://git.savannah.gnu.org/srv/git/perl-pesel.git'} + third_input = {} + + assert (priority_origin_url(first_input) == + 'https://kernel.googlesource.com/pub/scm/docs/man-pages/' + 'man-pages.git') + assert (priority_origin_url(second_input) == + 'git://git.savannah.gnu.org/perl-pesel.git') + assert priority_origin_url(third_input) is None + + +def test_find_netloc(): + first_url = urlparse('http://git.savannah.gnu.org/cgit/') + second_url = urlparse('https://cgit.kde.org/') + + assert find_netloc(first_url) == 'http://git.savannah.gnu.org' + assert find_netloc(second_url) == 'https://cgit.kde.org' diff --git a/swh/lister/cgit/tests/test_tasks.py b/swh/lister/cgit/tests/test_tasks.py new file mode 100644 --- /dev/null +++ b/swh/lister/cgit/tests/test_tasks.py @@ -0,0 +1,29 @@ +from unittest.mock import patch + + +def test_ping(swh_app, celery_session_worker): + res = swh_app.send_task( + 'swh.lister.cgit.tasks.ping') + assert res + res.wait() + assert res.successful() + assert res.result == 'OK' + + +@patch('swh.lister.cgit.tasks.CGitLister') +def test_lister(lister, swh_app, celery_session_worker): + # setup the mocked CGitLister + lister.return_value = lister + lister.run.return_value = None + + res = swh_app.send_task( + 'swh.lister.cgit.tasks.CGitListerTask') + assert res + res.wait() + assert res.successful() + + lister.assert_called_once_with( + base_url='https://git.savannah.gnu.org/cgit/', + instance='savannah-gnu') + lister.db_last_index.assert_not_called() + lister.run.assert_called_once_with() diff --git a/swh/lister/cli.py b/swh/lister/cli.py --- a/swh/lister/cli.py +++ b/swh/lister/cli.py @@ -12,7 +12,7 @@ logger = logging.getLogger(__name__) SUPPORTED_LISTERS = ['github', 'gitlab', 'bitbucket', 'debian', 'pypi', - 'npm', 'phabricator', 'gnu', 'cran'] + 'npm', 'phabricator', 'gnu', 'cran', 'cgit'] @click.group(name='lister', context_settings=CONTEXT_SETTINGS) @@ -125,6 +125,13 @@ from .cran.lister import CRANLister _lister = CRANLister(override_config=override_conf) + elif lister == 'cgit': + from .cgit.models import ModelBase + from .cgit.lister import CGitLister + _lister = CGitLister( + base_url='http://git.savannah.gnu.org/cgit/', + override_config=override_conf) + else: raise ValueError( 'Invalid lister %s: only supported listers are %s' % diff --git a/swh/lister/core/tests/conftest.py b/swh/lister/core/tests/conftest.py --- a/swh/lister/core/tests/conftest.py +++ b/swh/lister/core/tests/conftest.py @@ -6,6 +6,7 @@ def celery_includes(): return [ 'swh.lister.bitbucket.tasks', + 'swh.lister.cgit.tasks', 'swh.lister.cran.tasks', 'swh.lister.debian.tasks', 'swh.lister.github.tasks',