Page MenuHomeSoftware Heritage
Differential D5295 Diff 19079 swh/indexer/metadata_dictionary/maven.py

Changeset View

Standalone View

View Options

swh/indexer/metadata_dictionary/maven.py

# Copyright (C) 2018-2019 The Software Heritage developers # Copyright (C) 2018-2019 The Software Heritage developers
# See the AUTHORS file at the top-level directory of this distribution # See the AUTHORS file at the top-level directory of this distribution
# License: GNU General Public License version 3, or any later version # License: GNU General Public License version 3, or any later version
# See top-level LICENSE file for more information # See top-level LICENSE file for more information
import os import os
from typing import Any, Dict, List, Optional from typing import Any, Dict, List, Optional, Tuple, Union
import xml.parsers.expat import xml.parsers.expat
import xmltodict import xmltodict
from swh.indexer.codemeta import CROSSWALK_TABLE, SCHEMA_URI from swh.indexer.codemeta import CROSSWALK_TABLE, SCHEMA_URI
from .base import DictMapping, SingleFileMapping from .base import DictMapping, SingleFileMapping
class MavenMapping(DictMapping, SingleFileMapping): class MavenMapping(DictMapping, SingleFileMapping):
""" """
dedicated class for Maven (pom.xml) mapping and translation dedicated class for Maven (pom.xml) mapping and translation
""" """
name = "maven" name = "maven"
filename = b"pom.xml" filename = b"pom.xml"
mapping = CROSSWALK_TABLE["Java (Maven)"] mapping = CROSSWALK_TABLE["Java (Maven)"]
string_fields = ["name", "version", "description", "email"] string_fields = ["name", "version", "description", "email"]
def translate(self, content: bytes) -> Optional[Dict[str, Any]]: def translate(
self, content: bytes
) -> Optional[Dict[str, Union[str, List[Any], Dict[str, Any], Tuple[str]]]]:
try: try:
d = xmltodict.parse(content).get("project") or {} d = xmltodict.parse(content).get("project") or {}
except xml.parsers.expat.ExpatError: except xml.parsers.expat.ExpatError:
self.log.warning("Error parsing XML from %s", self.log_suffix) self.log.warning("Error parsing XML from %s", self.log_suffix)
return None return None
except UnicodeDecodeError: except UnicodeDecodeError:
self.log.warning("Error unidecoding XML from %s", self.log_suffix) self.log.warning("Error unidecoding XML from %s", self.log_suffix)
return None return None
except (LookupError, ValueError): except (LookupError, ValueError):
# unknown encoding or multi-byte encoding # unknown encoding or multi-byte encoding
self.log.warning("Error detecting XML encoding from %s", self.log_suffix) self.log.warning("Error detecting XML encoding from %s", self.log_suffix)
return None return None
metadata = self._translate_dict(d, normalize=False) metadata = self._translate_dict(d, normalize=False)
metadata[SCHEMA_URI + "codeRepository"] = self.parse_repositories(d) metadata[SCHEMA_URI + "codeRepository"] = self.parse_repositories(d)
metadata[SCHEMA_URI + "license"] = self.parse_licenses(d) metadata[SCHEMA_URI + "license"] = self.parse_licenses(d)
return self.normalize_translation(metadata) return self.normalize_translation(metadata)
_default_repository = {"url": "https://repo.maven.apache.org/maven2/"} _default_repository = {"url": "https://repo.maven.apache.org/maven2/"}
def parse_repositories(self, d: Dict[str, Any]) -> Optional[List[Any]]: def parse_repositories(self, d: Dict[str, Any]) -> Optional[List[Dict[str, str]]]:
"""https://maven.apache.org/pom.html#Repositories """https://maven.apache.org/pom.html#Repositories
>>> import xmltodict >>> import xmltodict
>>> from pprint import pprint >>> from pprint import pprint
>>> d = xmltodict.parse(''' >>> d = xmltodict.parse('''
... <repositories> ... <repositories>
... <repository> ... <repository>
... <id>codehausSnapshots</id> ... <id>codehausSnapshots</id>
Show All 12 Lines def parse_repositories(self, d: Dict[str, Any]) -> Optional[List[Dict[str, str]]]:
repositories = repositories.get("repository") or [] repositories = repositories.get("repository") or []
if not isinstance(repositories, list): if not isinstance(repositories, list):
repositories = [repositories] repositories = [repositories]
results = [self.parse_repository(d, repo) for repo in repositories] results = [self.parse_repository(d, repo) for repo in repositories]
else: else:
results = [] results = []
return [res for res in results if res] or None return [res for res in results if res] or None
def parse_repository(self, d: Dict[str, Any], repo: Dict[str, Any]) -> Any: def parse_repository(
self, d: Dict[str, Any], repo: Dict[str, Any]
) -> Optional[Dict[str, str]]:
if not isinstance(repo, dict): if not isinstance(repo, dict):
return return None
if repo.get("layout", "default") != "default": if repo.get("layout", "default") != "default":
return None # TODO ? return None # TODO ?
url = repo.get("url") url = repo.get("url")
group_id = d.get("groupId") group_id = d.get("groupId")
artifact_id = d.get("artifactId") artifact_id = d.get("artifactId")
if ( if (
isinstance(url, str) isinstance(url, str)
and isinstance(group_id, str) and isinstance(group_id, str)
and isinstance(artifact_id, str) and isinstance(artifact_id, str)
): ):
return {"@id": os.path.join(url, *group_id.split("."), artifact_id)} return {"@id": os.path.join(url, *group_id.split("."), artifact_id)}
else:
return None
def normalize_groupId(self, id_: str) -> Dict[str, str]: def normalize_groupId(self, id_: str) -> Dict[str, str]:
"""https://maven.apache.org/pom.html#Maven_Coordinates """https://maven.apache.org/pom.html#Maven_Coordinates
>>> MavenMapping().normalize_groupId('org.example') >>> MavenMapping().normalize_groupId('org.example')
{'@id': 'org.example'} {'@id': 'org.example'}
""" """
if isinstance(id_, str): if isinstance(id_, str):
▲ Show 20 Lines • Show All 61 Lines • Show Last 20 Lines
About · Developer information · Legal