feat: added functions for NASA Earthdata AWS S3 endpoints#222
Merged
Conversation
Contributor
There was a problem hiding this comment.
Pull request overview
Adds new utility helpers to support NASA Earthdata Cumulus AWS S3 access and JSON HTTP responses within timescale’s existing networking/IO utilities.
Changes:
- Added optional-dependency helpers (
import_dependency,dependency_available) and a URL validator. - Added
from_jsonfor loading JSON responses from HTTP(S) endpoints. - Added initial helpers for NASA Earthdata Cumulus S3 access (
s3_client,s3_region,s3_bucket,s3_key) and updated related provider/bucket mappings.
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
Contributor
|
Contributor
|
Contributor
|
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
chore: bump `pixi.lock` to version 7 chore: bump ci tools to newer versions
feat: add check to see if delta time file needs updating feat: add arguments to allow anonymous ftp use
Contributor
There was a problem hiding this comment.
Pull request overview
Copilot reviewed 12 out of 15 changed files in this pull request and generated 10 comments.
Comments suppressed due to low confidence (1)
timescale/utilities.py:1244
- In
attempt_login,promptis computed once from the initialusername, but inside the retry loop the code re-prompts for a newusernameand then callsgetpass.getpass(prompt=prompt)without recomputing it. This can display the wrong username in the password prompt on retries; recomputepromptafter updatingusernameinside the loop.
prompt = f"Password for {username}@{urs}: "
if not password:
password = getpass.getpass(prompt=prompt)
# host for endpoint
HOST = kwargs.get("endpoint")
# for each retry
for retry in range(kwargs["retries"]):
# build an opener for urs with credentials
opener = build_opener(
username,
password,
context=context,
password_manager=password_manager,
get_ca_certs=get_ca_certs,
redirect=redirect,
authorization_header=authorization_header,
urs=urs,
)
# try logging in by check credentials
try:
check_credentials(HOST)
except Exception as exc:
pass
else:
return opener
# reattempt login
username = builtins.input(f"Username for {urs}: ")
password = getpass.getpass(prompt=prompt)
# reached end of available retries
Comment on lines
+215
to
+222
| # check if module is available | ||
| if importlib.util.find_spec(name) is None: | ||
| return False | ||
| # check if the version is greater than the minimum required | ||
| if minversion is not None: | ||
| version = importlib.metadata.version(name) | ||
| return version >= minversion | ||
| # return if both checks are passed |
| local: str | pathlib.Path | None = None, | ||
| hash: str = "", | ||
| chunk: int = 16384, | ||
| headers: dict = {}, |
Comment on lines
+1061
to
+1066
| def from_json( | ||
| HOST: str | list, | ||
| timeout: int | None = None, | ||
| context: ssl.SSLContext = _default_ssl_context, | ||
| headers: dict = {}, | ||
| ) -> dict: |
Comment on lines
+112
to
+117
| Get a URL for the raw content of an item in the project repository | ||
|
|
||
| Parameters | ||
| ---------- | ||
| relpath: list or str | ||
| Relative path |
Comment on lines
+1508
to
+1512
| AWS region name | ||
| """ | ||
| boto3 = import_dependency("boto3") | ||
| region_name = boto3.session.Session().region_name | ||
| return region_name |
Comment on lines
+1554
to
+1571
| # PURPOSE: get a s3 bucket name from a presigned url | ||
| def s3_bucket(presigned_url: str) -> str: | ||
| """ | ||
| Get a s3 bucket name from a presigned url | ||
|
|
||
| Parameters | ||
| ---------- | ||
| presigned_url: str | ||
| s3 presigned url | ||
|
|
||
| Returns | ||
| ------- | ||
| bucket: str | ||
| s3 bucket name | ||
| """ | ||
| host = url_split(presigned_url) | ||
| bucket = re.sub(r"s3:\/\/", r"", host[0], re.IGNORECASE) | ||
| return bucket |
| """ | ||
| # check if the module name is a string | ||
| msg = f"Invalid module name: '{name}'; must be a string" | ||
| assert isinstance(name, str), msg |
Comment on lines
+231
to
+237
| # check if module is available | ||
| if importlib.util.find_spec(name) is None: | ||
| return False | ||
| # check if the version is greater than the minimum required | ||
| if minversion is not None: | ||
| version = importlib.metadata.version(name) | ||
| return version >= minversion |
| local: str | pathlib.Path | None = None, | ||
| hash: str = "", | ||
| chunk: int = 16384, | ||
| headers: dict = {}, |
Comment on lines
1007
to
+1054
| @@ -833,15 +1036,22 @@ def from_http( | |||
| # Create and submit request. | |||
| request = urllib2.Request(posixpath.join(*HOST), **kwargs) | |||
| response = urllib2.urlopen(request, timeout=timeout, context=context) | |||
| except: | |||
| raise Exception("Download error from {0}".format(posixpath.join(*HOST))) | |||
| except urllib2.HTTPError as exc: | |||
| logging.debug(exc.code) | |||
| raise | |||
| except urllib2.URLError as exc: | |||
| logging.debug(exc.reason) | |||
| exc.message = "Check internet connection" | |||
| raise | |||
| else: | |||
| # copy remote file contents to bytesIO object | |||
| remote_buffer = io.BytesIO() | |||
| shutil.copyfileobj(response, remote_buffer, chunk) | |||
| remote_buffer.seek(0) | |||
| # save file basename with bytesIO object | |||
| remote_buffer.filename = HOST[-1] | |||
| # copy headers from response | |||
| headers.update({k.lower(): v for k, v in response.getheaders()}) | |||
Comment on lines
+1077
to
+1082
| def from_json( | ||
| HOST: str | list, | ||
| timeout: int | None = None, | ||
| context: ssl.SSLContext = _default_ssl_context, | ||
| headers: dict = {}, | ||
| ) -> dict: |
Comment on lines
+1524
to
+1528
| AWS region name | ||
| """ | ||
| boto3 = import_dependency("boto3") | ||
| region_name = boto3.session.Session().region_name | ||
| return region_name |
Comment on lines
+1554
to
+1565
| request = urllib2.Request(HOST) | ||
| response = urllib2.urlopen(request, timeout=timeout) | ||
| cumulus = json.loads(response.read()) | ||
| # get AWS client object | ||
| boto3 = import_dependency("boto3") | ||
| client = boto3.client( | ||
| "s3", | ||
| aws_access_key_id=cumulus["accessKeyId"], | ||
| aws_secret_access_key=cumulus["secretAccessKey"], | ||
| aws_session_token=cumulus["sessionToken"], | ||
| region_name=region_name, | ||
| ) |
Comment on lines
+1604
to
+1641
| def update_delta_time( | ||
| delta_file: str | pathlib.Path, | ||
| branch: str = "main", | ||
| verbose: bool = False, | ||
| mode: oct = 0o775, | ||
| ): | ||
| """ | ||
| Downloads an updated delta time file from the project GitHub repository | ||
|
|
||
| Parameters | ||
| ---------- | ||
| delta_file: str or Pathlib.Path | ||
| file containing the delta times (TT-UT1) | ||
| branch: str, default 'main' | ||
| branch of the GitHub repository to download from | ||
| verbose: bool, default False | ||
| print file information about output file | ||
| mode: oct, default 0o775 | ||
| permissions mode of output file | ||
|
|
||
| Notes | ||
| ----- | ||
| Delta times are the difference between dynamical time and universal time | ||
| """ | ||
| # verify delta time file path | ||
| delta_file = pathlib.Path(delta_file).expanduser().absolute() | ||
| # MD5 hash for comparing with remote | ||
| HASH = timescale.utilities.get_hash(delta_file) | ||
| # try downloading from GitHub repository | ||
| HOST = timescale.utilities.get_github_url( | ||
| ["timescale", "data", delta_file.name], branch=branch | ||
| ) | ||
| # log message for failed download | ||
| msg = f"Unable to download {delta_file.name} from timescale repository" | ||
| try: | ||
| timescale.utilities.from_http( | ||
| HOST, local=delta_file, hash=HASH, verbose=verbose, mode=mode | ||
| ) |
Comment on lines
+110
to
+148
| def get_github_url( | ||
| relpath: list | str, | ||
| username: str = "pyTMD", | ||
| repository: str = "timescale", | ||
| branch: str = "main", | ||
| ): | ||
| """ | ||
| Get the URL of an item's raw content from a GitHub repository | ||
|
|
||
| Parameters | ||
| ---------- | ||
| relpath: list or str | ||
| Relative path | ||
| username: str, default 'pyTMD' | ||
| GitHub username for project repository | ||
| repository: str, default 'timescale' | ||
| GitHub project name | ||
| branch: str, default 'main' | ||
| GitHub branch name | ||
|
|
||
| Returns | ||
| ------- | ||
| raw_url: str | ||
| item URL | ||
| """ | ||
| # components of the URL for raw content from the project repository | ||
| HOST = [ | ||
| "https://raw.githubusercontent.com", | ||
| username, | ||
| repository, | ||
| "refs", | ||
| "heads", | ||
| branch, | ||
| ] | ||
| # check if relative path is a string and convert to list | ||
| if isinstance(relpath, str): | ||
| relpath = [relpath] | ||
| # append the relative path components to the URL | ||
| return "/".join(HOST + relpath) |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
No description provided.