diff --git a/mypy.ini b/mypy.ini --- a/mypy.ini +++ b/mypy.ini @@ -36,3 +36,7 @@ [mypy-urllib3.util.*] ignore_missing_imports = True + +[mypy-xmltodict.*] +ignore_missing_imports = True + diff --git a/requirements.txt b/requirements.txt --- a/requirements.txt +++ b/requirements.txt @@ -5,3 +5,4 @@ beautifulsoup4 launchpadlib tenacity +xmltodict diff --git a/setup.py b/setup.py --- a/setup.py +++ b/setup.py @@ -71,6 +71,7 @@ lister.pypi=swh.lister.pypi:register lister.sourceforge=swh.lister.sourceforge:register lister.tuleap=swh.lister.tuleap:register + lister.maven=swh.lister.maven:register """, classifiers=[ "Programming Language :: Python :: 3", diff --git a/swh/lister/maven/README.md b/swh/lister/maven/README.md new file mode 100644 --- /dev/null +++ b/swh/lister/maven/README.md @@ -0,0 +1,142 @@ + +## The Maven lister + +This readme describes the design decisions made during development. + +More information can be found on the Software Heritage forge at [https://forge.softwareheritage.org/T1724](https://forge.softwareheritage.org/T1724) and on the diff of the lister at [https://forge.softwareheritage.org/D6133](https://forge.softwareheritage.org/D6133) . + +## Execution sequence (TL;DR) + +The complete sequence of actions to list the source artifacts and scm urls is as follows: + +On the `index_exporter` server (asynchronously): + +* Check the list of remote indexes, and compare it to the list of local index files. +* Retrieve the missing Maven Indexer indexes from the remote repository. \ + Example of index from Maven Central: [https://repo1.maven.org/maven2/.index/](https://repo1.maven.org/maven2/.index/) +* Start execution of the Docker container: + * If the `indexes` directory doesn't exist, unpack the Lucene indexes from the Maven Indexer indexes using `indexer-cli`.\ + This generates a set of binary files as shown below: + + ``` + boris@castalia:maven$ ls -lh /media/home2/work/indexes/ + total 5,2G + -rw-r--r-- 1 root root 500M juil. 7 22:06 _4m.fdt + -rw-r--r-- 1 root root 339K juil. 7 22:06 _4m.fdx + -rw-r--r-- 1 root root 2,2K juil. 7 22:07 _4m.fnm + -rw-r--r-- 1 root root 166M juil. 7 22:07 _4m_Lucene50_0.doc + -rw-r--r-- 1 root root 147M juil. 7 22:07 _4m_Lucene50_0.pos + -rw-r--r-- 1 root root 290M juil. 7 22:07 _4m_Lucene50_0.time + -rw-r--r-- 1 root root 3,1M juil. 7 22:07 _4m_Lucene50_0.tip + [SNIP] + -rw-r--r-- 1 root root 363 juil. 7 22:06 _e0.si + -rw-r--r-- 1 root root 1,7K juil. 7 22:07 segments_2 + -rw-r--r-- 1 root root 8 juil. 7 21:54 timestamp + -rw-r--r-- 1 root root 0 juil. 7 21:54 write.lock + ``` + * If the `export` directory doesn't exist, export the Lucene documents from the Lucene indexes using `clue`.\ + This generates a set of text files as shown below: + + ``` + boris@castalia:~$ ls -lh /work/export/ + total 49G + -rw-r--r-- 1 root root 13G juil. 7 22:12 _p.fld + -rw-r--r-- 1 root root 7,0K juil. 7 22:21 _p.inf + -rw-r--r-- 1 root root 2,9G juil. 7 22:21 _p.len + -rw-r--r-- 1 root root 33G juil. 7 22:20 _p.pst + -rw-r--r-- 1 root root 799 juil. 7 22:21 _p.si + -rw-r--r-- 1 root root 138 juil. 7 22:21 segments_1 + -rw-r--r-- 1 root root 0 juil. 7 22:07 write.lock + ``` +* On the host, copy export files to `/var/www/html/` to make them available on the network. + +On the lister side: + +* Get the exports from the above local index server. +* Extract the list of all pom and source artefacts from the Lucene export. +* Yield the list of source artefacts to the Maven Loader as they are found. +* Download all poms from the above list. +* Parse all poms to extract the scm attribute, and yield the list of scm urls towards the classic loaders (git, svn, hg..). + +The process has been optimised as much as it could be, scaling down from 140 GB on disk / 60 GB RAM / 90 mn exec time to 60 GB on disk / 2 GB (excl. docker) / 32 mn exec time. + +For the long read about why we came to here, please continue. + +## About the Maven ecosystem + +Maven repositories are a loose, decentralised network of HTTP servers with a well-defined hosted structure. They are used according to the Maven dependency resolver[i](#sdendnote1sym), an inheritance-based mechanism used to identify and locate artefacts required in Maven builds. + +There is no uniform, standardised way to list the contents of maven repositories, since consumers are supposed to know what artefacts they need. Instead, Maven repository owners usually setup a Maven Indexer[ii](#sdendnote2sym) to enablesource code identification and listing in IDEs – for this reason, source jars usually don’t have build files and information, only providing pure sources. + +Maven Indexer is not a mandatory part of the maven repository stack, but it is the *de facto* standard for maven repositories indexing and querying. All major Maven repositories we have seen so far use it. Most artefacts are located in the main central repository: Maven Central[iii](#sdendnote3sym), hosted and run by Sonatype[iv](#sdendnote4sym). Other well-known repositories are listed on MVN Repository[v](#sdendnote5sym). + +Maven repositories are mainly used for binary content (e.g. class jars), but the following sources of information are relevant to our goal in the maven repositories/ecosystem: + +* SCM attributes in pom XML files contain the **scm URL** of the associated source code. They can be fed to standard Git/SVN/others loaders. +* **Source artefacts** contain pure source code (i.e. no build files) associated to the artefact. There are two main naming conventions for them, although not always enforced: + * ${artifactId}-${version}-source-release.zip + * ${artifactId}-${version}-src.zip + + They come in various archiving formats (jar, zip, tar.bz2, tar.gz) and require a specific loader to attach the artefact metadata. + +[i](#sdendnote1anc)Maven dependency resolver: [https://maven.apache.org/resolver/index.html](https://maven.apache.org/resolver/index.html) + +[ii](#sdendnote2anc)Maven Indexer: [https://maven.apache.org/maven-indexer/](https://maven.apache.org/maven-indexer/) + +[iii](#sdendnote3anc)Maven Central: [https://search.maven.org/](https://search.maven.org/) + +[iv](#sdendnote4anc)Sonatype Company: [https://www.sonatype.com/](https://www.sonatype.com/) + +[v](#sdendnote5anc)MVN Repository: [https://mvnrepository.com/repos](https://mvnrepository.com/repos) + +## Preliminary research + +Listing the full content of a Maven repository is very unusual, and the whole system has not been built for this purpose. Instead, tools and build systems can easily fetch individual artefacts according to their Maven coordinates (groupId, artifactId, version, classifier, extension). Usual listing means (e.g. scapping) are highly discouraged and will trigger bannishment easily. There is no common API defined either. + +Once we have the artifactId/group we can easily get the list of versions (e.g. for updates) by reading the [maven-metadata.xml file at the package level](https://repo1.maven.org/maven2/ant/ant/maven-metadata.xml), although this is not always reliable. The various options that were investigated to get the interesting artefacts are: + +* **Scrapping** could work but is explicitly forbidden[i](#sdendnote1sym). Pages could easily be parsed through, and it would allow to identify \*all\* artifacts. +* Using **Maven indexes** is the "official" way to retrieve information from a maven repository and most repositories provide this feature. It would also enable a smart incremental listing. The Maven Indexer data format however is not we + ll documented. It relies under the hood on an old version (Lucene54) of a lucene indexes, and the only libraries that can access it are written in java. This implies a dedicated Docker container with a jvm and some specific tools (maven indexer and luke for the lucene index), and thus would bring some complexity to the docker & prod setups. +* A third path could be to **parse all the pom.xml's** that we find and follow all artifactId's recursively, building a graph of dependencies and parent poms. This is more of a non-complete heuristic, and we would miss leaf nodes (i.e. artifacts that are not used by others), but it could help setup a basic list. +* It should be noted also that there are two main implementations of maven repositories: Nexus and Artifactory. By being more specific we could use the respective APIs of these products to get information. But getting the full list of artefacts is still not straightforward, and we'd lose any generic treatment doing so. + +The best option in our opinion is to go with the Maven Indexer, for it is the most complete listing available (notably for the biggest repository by far: maven central). + +[i](#sdendnote1anc)Maven repository’s Terms of Service: [https://repo1.maven.org/terms.html](https://repo1.maven.org/terms.html) + +## Maven indexes conversion + +[Maven-Indexer](https://maven.apache.org/maven-indexer/) is a (thick) wrapper around lucene. It parses the repository and stores documents, fields and terms in an index. One can extract the lucene index from a maven index using the command: `java -jar indexer-cli-5.1.1.jar --unpack nexus-maven-repository-index.gz --destination test --type full`. Note however that 5.1.1 is an old version of maven indexer; newer versions of the maven indexer won't work on the central indexes. + +[Clue](https://maven.apache.org/maven-indexer/) is a CLI tool to read lucene indexes, and version 6.2.0 works with our maven indexes. One can use the following command to export the index to text: `java -jar clue-6.2.0-1.0.0.jar maven/central-lucene-index/ export central_export text`. + +The exported text file looks like this: + +``` +doc 0 + field 0 + name u + type string + value com.redhat.rhevm.api|rhevm-api-powershell-jaxrs|1.0-rc1.16|javadoc|jar + field 1 + name m + type string + value 1321264789727 + field 2 + name i + type string + value jar|1320743675000|768291|2|2|1|jar + field 10 + name n + type string + value RHEV-M API Powershell Wrapper Implementation JAX-RS + field 13 + name 1 + type string + value 454eb6762e5bb14a75a21ae611ce2048dd548550 +``` + +The execution of these two jars requires a Java virtual machine -- java execution in python is not possible without a JVM. Docker is a good way to run both tools and generate the exports independently, rather than add a JVM to the existing production environment. + +We decided (2021-08-25) to install and execute a docker container on a separate server so the lister would simply have to fetch it on the network and parse it (the latter part in pure python). diff --git a/swh/lister/maven/__init__.py b/swh/lister/maven/__init__.py new file mode 100644 --- /dev/null +++ b/swh/lister/maven/__init__.py @@ -0,0 +1,12 @@ +# Copyright (C) 2021 the Software Heritage developers +# License: GNU General Public License version 3, or any later version +# See top-level LICENSE file for more information + + +def register(): + from .lister import MavenLister + + return { + "lister": MavenLister, + "task_modules": ["%s.tasks" % __name__], + } diff --git a/swh/lister/maven/lister.py b/swh/lister/maven/lister.py new file mode 100644 --- /dev/null +++ b/swh/lister/maven/lister.py @@ -0,0 +1,266 @@ +# Copyright (C) 2021 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 collections import defaultdict +import logging +import re +from tempfile import NamedTemporaryFile +from typing import Any, Dict, Iterator, Optional +from urllib.parse import urljoin + +import requests +from tenacity.before_sleep import before_sleep_log +from urllib3.util import parse_url +import xmltodict + +from swh.lister.utils import throttling_retry +from swh.scheduler.interface import SchedulerInterface +from swh.scheduler.model import ListedOrigin + +from .. import USER_AGENT +from ..pattern import CredentialsType, StatelessLister + +logger = logging.getLogger(__name__) + +RepoPage = Dict[str, Any] + + +class MavenLister(StatelessLister[RepoPage]): + """List origins from a Maven repository. + + Maven Central provides artifacts for Java builds. + It includes POM files and source archives, which we download to get + the source code of artifacts and links to their scm repository. + + This lister yields origins of types: git/svn/hg or whatever the Artifacts + use as repository type, plus maven types for the maven loader (tgz, jar).""" + + LISTER_NAME = "maven" + + def __init__( + self, + scheduler: SchedulerInterface, + url: str, + index_url: str = None, + instance: Optional[str] = None, + credentials: CredentialsType = None, + ): + """Lister class for Maven repositories. + + Args: + url: main URL of the Maven repository, i.e. url of the base index + used to fetch maven artifacts. For Maven central use + https://repo1.maven.org/maven2/ + index_url: the URL to download the exported text indexes from. + Would typically be a local host running the export docker image. + instance: Name of maven instance. Defaults to url's network location + if unset. + + """ + self.BASE_URL = url + self.INDEX_URL = index_url + + if instance is None: + instance = parse_url(url).host + + super().__init__( + scheduler=scheduler, credentials=credentials, url=url, instance=instance, + ) + + self.session = requests.Session() + self.session.headers.update( + {"Accept": "application/json", "User-Agent": USER_AGENT,} + ) + + @throttling_retry(before_sleep=before_sleep_log(logger, logging.WARNING)) + def page_request(self, url: str, params: Dict[str, Any]) -> requests.Response: + + logger.info("Fetching URL %s with params %s", url, params) + + response = self.session.get(url, params=params) + if response.status_code != 200: + logger.warning( + "Unexpected HTTP status code %s on %s: %s", + response.status_code, + response.url, + response.content, + ) + response.raise_for_status() + + return response + + def get_pages(self) -> Iterator[RepoPage]: + """ Retrieve and parse exported maven indexes to + identify all pom files and src archives. + + """ + + # Example of returned RepoPage's: + # [ + # { + # "type": "jar", + # "url": "https://maven.xwiki.org/..-5.4.2-sources.jar", + # "time": 1626109619335, + # "gid": "org.xwiki.platform", + # "aid": "xwiki-platform-wikistream-events-xwiki", + # "version": "5.4.2" + # }, + # { + # "type": "scm", + # "url": "scm:git:git://github.com/openengsb/openengsb-framework.git", + # "project": "openengsb-framework", + # }, + # ... + # ] + + # Download the main text index file. + logger.info("Downloading text index file..") + text_file = NamedTemporaryFile(delete=False) + assert self.INDEX_URL is not None + response = requests.get(self.INDEX_URL, stream=True) + + # Prepare regex's to parse index exports. + re_val = re.compile(r"^\s{4}value ([^|]+)\|([^|]+)\|([^|]+)\|([^|]+)\|([^|]+)$") + re_time = re.compile( + r"^\s{4}value ([^|]+)\|([^|]+)\|([^|]+)\|([^|]+)\|([^|]+)" + + r"\|([^|]+)\|([^|]+)$" + ) + re_src = re.compile(r".*src.*") + + # Read file line by line and process it + out_pom: Dict = defaultdict(dict) + out_src: Dict = defaultdict(dict) + url_src = None + + iterator = response.iter_lines(chunk_size=1024) + for line_bytes in iterator: + # Read the index text export and get URLs and SCMs. + line = line_bytes.decode() + print(f"DBG Line {line}.") + m_val = re_val.match(line) + if m_val is not None: + (gid, aid, version, classifier, ext) = m_val.group(1, 2, 3, 4, 5) + ext = ext.strip() + path = "/".join(gid.split(".")) + if classifier == "NA" and ext.lower() == "pom": + url_path = f"{path}/{aid}/{version}/{aid}-{version}.{ext}" + url_pom = urljoin(self.BASE_URL, url_path,) + out_pom[url_pom] = aid + print(f"DBG Found {url_pom}.") + elif ( + classifier.lower() == "sources" or re_src.match(classifier) + ) and ext.lower() in ("zip", "jar"): + url_path = ( + f"{path}/{aid}/{version}/" f"{aid}-{version}-{classifier}.{ext}" + ) + url_src = urljoin(self.BASE_URL, url_path) + print(f"DBG Found {url_src} {gid} {aid} {version}.") + out_src[url_src]["g"] = gid + out_src[url_src]["a"] = aid + out_src[url_src]["v"] = version + else: + m_time = re_time.match(line) + if m_time is not None and url_src is not None: + time = m_time.group(2) + print(f"DBG Found {url_src} time {int(time)}.") + out_src[url_src]["t"] = int(time) + url_src = None + line_bytes = next(iterator) + text_file.close() + + logger.info(f"Found {len(out_pom)} poms and {len(out_src)} src items.") + + # Yield all src archives found. + for src in out_src.keys(): + logger.debug(f"* Yielding jar {src}.") + print(f"* Yielding jar {src}.") + yield { + "type": "jar", + "url": src, + "time": out_src[src]["t"], + "gid": out_src[src]["g"], + "aid": out_src[src]["a"], + "version": out_src[src]["v"], + } + + # Now fetch pom files and scan them for scm info. + + logger.info("Fetching poms..") + out_pom_src = {} + for pom in out_pom.keys(): + text = self.page_request(pom, {}) + try: + project = xmltodict.parse(text.content.decode()) + if "scm" in project["project"]: + if "connection" in project["project"]["scm"]: + scm = project["project"]["scm"]["connection"] + gid = project["project"]["groupId"] + aid = project["project"]["artifactId"] + out_pom_src[scm] = f"{gid}.{aid}" + else: + logger.debug(f"No scm.connection in pom {pom}") + else: + logger.debug(f"No scm in pom {pom}") + except xmltodict.expat.ExpatError as error: + logger.info(f"Could not parse POM {pom} XML: {error}. Next.") + + # Yield all src archives found. + for src in out_pom_src.keys(): + logger.debug(f"* Yielding scm {src}.") + yield { + "type": "scm", + "url": src, + "project": out_pom_src[src], + } + + def get_origins_from_page(self, page: RepoPage) -> Iterator[ListedOrigin]: + """Convert a page of Maven repositories into a list of ListedOrigins. + + """ + assert self.lister_obj.id is not None + if page["type"] == "scm": + # If origin is a scm url: detect scm type and yield. + # Note that the official format is: + # scm:git:git://github.com/openengsb/openengsb-framework.git + # but many, many projects directly put the repo url, so we have to + # detect the content to match it properly. + re_scm = re.compile(r"^scm:([^:]+):(.*)$") + m_scm = re_scm.match(page["url"]) + if m_scm is not None: + scm_type = m_scm.group(1) + scm_url = m_scm.group(2) + origin = ListedOrigin( + lister_id=self.lister_obj.id, + url=scm_url, # or page["url"], + visit_type=scm_type, + ) + yield origin + else: + re_scm = re.compile(r".*\.git$") + m_scm = re_scm.match(page["url"]) + if m_scm is not None: + origin = ListedOrigin( + lister_id=self.lister_obj.id, url=page["url"], visit_type="git", + ) + yield origin + else: + # Origin is a source archive: + origin = ListedOrigin( + lister_id=self.lister_obj.id, + url=page["url"], + visit_type=page["type"], + # last_update=parse_packaged_date(package_info), + extra_loader_arguments={ + "artifacts": [ + { + "time": page["time"], + "gid": page["gid"], + "aid": page["aid"], + "version": page["version"], + } + ] + }, + ) + yield origin diff --git a/swh/lister/maven/tasks.py b/swh/lister/maven/tasks.py new file mode 100644 --- /dev/null +++ b/swh/lister/maven/tasks.py @@ -0,0 +1,21 @@ +# Copyright (C) 2021 the Software Heritage developers +# License: GNU General Public License version 3, or any later version +# See top-level LICENSE file for more information + +from typing import Dict + +from celery import shared_task + +from .lister import MavenLister + + +@shared_task(name=__name__ + ".FullMavenLister") +def list_maven_full(**lister_args) -> Dict[str, int]: + """Full update of a Maven repository instance""" + lister = MavenLister.from_configfile(**lister_args) + return lister.run().dict() + + +@shared_task(name=__name__ + ".ping") +def _ping() -> str: + return "OK" diff --git a/swh/lister/maven/tests/__init__.py b/swh/lister/maven/tests/__init__.py new file mode 100644 diff --git a/swh/lister/maven/tests/data/https_indexes/export.fld b/swh/lister/maven/tests/data/https_indexes/export.fld new file mode 100755 --- /dev/null +++ b/swh/lister/maven/tests/data/https_indexes/export.fld @@ -0,0 +1,113 @@ +doc 0 + field 0 + name u + type string + value al.aldi|sprova4j|0.1.0|sources|jar + field 1 + name m + type string + value 1626111735737 + field 2 + name i + type string + value jar|1626109619335|14316|2|2|0|jar + field 10 + name n + type string + value sprova4j + field 11 + name d + type string + value Java client for Sprova Test Management +doc 1 + field 0 + name u + type string + value al.aldi|sprova4j|0.1.0|NA|pom + field 1 + name m + type string + value 1626111735764 + field 2 + name i + type string + value jar|1626109636636|-1|1|0|0|pom + field 10 + name n + type string + value sprova4j + field 11 + name d + type string + value Java client for Sprova Test Management +doc 2 + field 0 + name u + type string + value al.aldi|sprova4j|0.1.1|sources|jar + field 1 + name m + type string + value 1626111784883 + field 2 + name i + type string + value jar|1626111425534|14510|2|2|0|jar + field 10 + name n + type string + value sprova4j + field 11 + name d + type string + value Java client for Sprova Test Management +doc 3 + field 0 + name u + type string + value al.aldi|sprova4j|0.1.1|NA|pom + field 1 + name m + type string + value 1626111784915 + field 2 + name i + type string + value jar|1626111437014|-1|1|0|0|pom + field 10 + name n + type string + value sprova4j + field 11 + name d + type string + value Java client for Sprova Test Management +doc 4 + field 14 + name DESCRIPTOR + type string + value NexusIndex + field 15 + name IDXINFO + type string + value 1.0|index +doc 5 + field 16 + name allGroups + type string + value allGroups + field 17 + name allGroupsList + type string + value al.aldi +doc 6 + field 18 + name rootGroups + type string + value rootGroups + field 19 + name rootGroupsList + type string + value al +END +checksum 00000000003321211082 diff --git a/swh/lister/maven/tests/data/https_maven.org/sprova4j-0.1.0.pom b/swh/lister/maven/tests/data/https_maven.org/sprova4j-0.1.0.pom new file mode 100644 --- /dev/null +++ b/swh/lister/maven/tests/data/https_maven.org/sprova4j-0.1.0.pom @@ -0,0 +1,86 @@ + + + 4.0.0 + al.aldi + sprova4j + 0.1.0 + sprova4j + Java client for Sprova Test Management + https://github.com/aldialimucaj/sprova4j + 2018 + + + The Apache Software License, Version 2.0 + http://www.apache.org/licenses/LICENSE-2.0.txt + repo + + + + + aldi + Aldi Alimucaj + aldi.alimucaj@gmail.com + + + + scm:git:git://github.com/aldialimucaj/sprova4j.git + scm:git:git://github.com/aldialimucaj/sprova4j.git + https://github.com/aldialimucaj/sprova4j + + + + ch.qos.logback + logback-classic + 1.2.3 + runtime + + + com.google.code.gson + gson + 2.8.3 + runtime + + + com.squareup.okhttp3 + okhttp + 3.10.0 + runtime + + + com.squareup.okio + okio + 1.0.0 + runtime + + + org.glassfish + javax.json + 1.1.2 + runtime + + + javax.json + javax.json-api + 1.1.2 + runtime + + + javax.validation + validation-api + 2.0.1.Final + runtime + + + junit + junit + 4.12 + test + + + com.squareup.okhttp3 + mockwebserver + 3.10.0 + test + + + diff --git a/swh/lister/maven/tests/data/https_maven.org/sprova4j-0.1.1.pom b/swh/lister/maven/tests/data/https_maven.org/sprova4j-0.1.1.pom new file mode 100644 --- /dev/null +++ b/swh/lister/maven/tests/data/https_maven.org/sprova4j-0.1.1.pom @@ -0,0 +1,86 @@ + + + 4.0.0 + al.aldi + sprova4j + 0.1.1 + sprova4j + Java client for Sprova Test Management + https://github.com/aldialimucaj/sprova4j + 2018 + + + The Apache Software License, Version 2.0 + http://www.apache.org/licenses/LICENSE-2.0.txt + repo + + + + + aldi + Aldi Alimucaj + aldi.alimucaj@gmail.com + + + + https://github.com/aldialimucaj/sprova4j.git + https://github.com/aldialimucaj/sprova4j.git + https://github.com/aldialimucaj/sprova4j + + + + ch.qos.logback + logback-classic + 1.2.3 + runtime + + + com.google.code.gson + gson + 2.8.5 + runtime + + + com.squareup.okhttp3 + okhttp + 3.10.0 + runtime + + + com.squareup.okio + okio + 1.14.1 + runtime + + + org.glassfish + javax.json + 1.1.2 + runtime + + + javax.json + javax.json-api + 1.1.2 + runtime + + + javax.validation + validation-api + 2.0.1.Final + runtime + + + junit + junit + 4.12 + test + + + com.squareup.okhttp3 + mockwebserver + 3.10.0 + test + + + diff --git a/swh/lister/maven/tests/test_lister.py b/swh/lister/maven/tests/test_lister.py new file mode 100644 --- /dev/null +++ b/swh/lister/maven/tests/test_lister.py @@ -0,0 +1,152 @@ +# Copyright (C) 2021 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 +from typing import List + +import pytest +import requests + +from swh.lister.maven.lister import MavenLister +from swh.scheduler.model import ListedOrigin + +MVN_URL = "https://repo1.maven.org/maven2/" # main maven repo url +INDEX_URL = "https://indexes/export.fld" # index directory url + +URL_POM_1 = MVN_URL + "al/aldi/sprova4j/0.1.0/sprova4j-0.1.0.pom" +URL_POM_2 = MVN_URL + "al/aldi/sprova4j/0.1.1/sprova4j-0.1.1.pom" + +LIST_SRC = ( + MVN_URL + "al/aldi/sprova4j/0.1.0/sprova4j-0.1.0-sources.jar", + MVN_URL + "al/aldi/sprova4j/0.1.1/sprova4j-0.1.1-sources.jar", +) + +LIST_SRC_DATA = ( + { + "type": "jar", + "url": "https://repo1.maven.org/maven2/al/aldi/sprova4j" + + "/0.1.0/sprova4j-0.1.0-sources.jar", + "time": 1626109619335, + "gid": "al.aldi", + "aid": "sprova4j", + "version": "0.1.0", + }, + { + "type": "jar", + "url": "https://repo1.maven.org/maven2/al/aldi/sprova4j" + + "/0.1.1/sprova4j-0.1.1-sources.jar", + "time": 1626111425534, + "gid": "al.aldi", + "aid": "sprova4j", + "version": "0.1.1", + }, +) + +LIST_GIT = ( + "git://github.com/aldialimucaj/sprova4j.git", + "https://github.com/aldialimucaj/sprova4j.git", +) + + +@pytest.fixture +def maven_index(datadir) -> str: + text = Path(datadir, "https_indexes", "export.fld").read_text() + return text + + +@pytest.fixture +def maven_pom_1(datadir) -> str: + text = Path(datadir, "https_maven.org", "sprova4j-0.1.0.pom").read_text() + return text + + +@pytest.fixture +def maven_pom_2(datadir) -> str: + text = Path(datadir, "https_maven.org", "sprova4j-0.1.1.pom").read_text() + return text + + +def check_listed_origins(lister_urls: List[str], scheduler_origins: List[ListedOrigin]): + """Asserts that the two collections have the same origin URLs. + + Does not test last_update.""" + + sorted_lister_urls = list(sorted(lister_urls)) + sorted_scheduler_origins = list(sorted(scheduler_origins, key=lambda x: x.url)) + + assert len(sorted_lister_urls) == len(sorted_scheduler_origins) + + for l_url, s_origin in zip(sorted_lister_urls, sorted_scheduler_origins): + assert l_url == s_origin.url + + +def test_maven_full_listing( + swh_scheduler, requests_mock, mocker, maven_index, maven_pom_1, maven_pom_2, +): + """Covers full listing of multiple pages, checking page results and listed + origins, statelessness.""" + + lister = MavenLister( + scheduler=swh_scheduler, url=MVN_URL, instance="maven.org", index_url=INDEX_URL, + ) + + index_text = maven_index + p1_text = maven_pom_1 + p2_text = maven_pom_2 + requests_mock.get(INDEX_URL, text=index_text) + requests_mock.get(URL_POM_1, text=p1_text) + requests_mock.get(URL_POM_2, text=p2_text) + + # end test setup + + stats = lister.run() + # start test checks + assert stats.pages == 4 + assert stats.origins == 4 + + scheduler_origins = swh_scheduler.get_listed_origins(lister.lister_obj.id).results + check_listed_origins(LIST_GIT + LIST_SRC, scheduler_origins) + for s in scheduler_origins: + if s.visit_type == "jar": + for list in LIST_SRC_DATA: + if list.get("url") == s.url: + assert ( + list.get("time") + == s.extra_loader_arguments["artifacts"][0]["time"] + ) + assert ( + list.get("gid") + == s.extra_loader_arguments["artifacts"][0]["gid"] + ) + assert ( + list.get("aid") + == s.extra_loader_arguments["artifacts"][0]["aid"] + ) + assert ( + list.get("version") + == s.extra_loader_arguments["artifacts"][0]["version"] + ) + break + else: + raise AssertionError + assert lister.get_state_from_scheduler() is None + + +@pytest.mark.parametrize("http_code", [400, 500, 502]) +def test_maven_list_http_error( + swh_scheduler, requests_mock, mocker, maven_index, http_code +): + """Test handling of some HTTP errors commonly encountered""" + + lister = MavenLister(scheduler=swh_scheduler, url=MVN_URL, index_url=INDEX_URL) + + requests_mock.get(INDEX_URL, text=maven_index) + requests_mock.get(URL_POM_1, status_code=http_code) + + with pytest.raises(requests.HTTPError): + lister.run() + + scheduler_origins = swh_scheduler.get_listed_origins(lister.lister_obj.id).results + assert len(scheduler_origins) == 2 diff --git a/swh/lister/maven/tests/test_tasks.py b/swh/lister/maven/tests/test_tasks.py new file mode 100644 --- /dev/null +++ b/swh/lister/maven/tests/test_tasks.py @@ -0,0 +1,33 @@ +# Copyright (C) 2021 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 swh.lister.pattern import ListerStats + + +def test_ping(swh_scheduler_celery_app, swh_scheduler_celery_worker): + res = swh_scheduler_celery_app.send_task("swh.lister.maven.tasks.ping") + assert res + res.wait() + assert res.successful() + assert res.result == "OK" + + +def test_full_listing(swh_scheduler_celery_app, swh_scheduler_celery_worker, mocker): + lister = mocker.patch("swh.lister.maven.tasks.MavenLister") + lister.from_configfile.return_value = lister + lister.run.return_value = ListerStats(pages=10, origins=500) + + kwargs = dict( + url="https://repo1.maven.org/maven2/", index_url="http://indexes/export.fld" + ) + res = swh_scheduler_celery_app.send_task( + "swh.lister.maven.tasks.FullMavenLister", kwargs=kwargs, + ) + assert res + res.wait() + assert res.successful() + + lister.from_configfile.assert_called_once_with(**kwargs) + lister.run.assert_called_once_with() diff --git a/swh/lister/tests/test_cli.py b/swh/lister/tests/test_cli.py --- a/swh/lister/tests/test_cli.py +++ b/swh/lister/tests/test_cli.py @@ -18,6 +18,10 @@ "tuleap": {"url": "https://tuleap.net",}, "gitlab": {"url": "https://gitlab.ow2.org/api/v4", "instance": "ow2",}, "opam": {"url": "https://opam.ocaml.org", "instance": "opam"}, + "maven": { + "url": "https://repo1.maven.org/maven2/", + "index_url": "https://indexes/export.fld", + }, }