dcicutils 8.8.4.1b13__tar.gz → 8.8.4.1b17__tar.gz

{dcicutils-8.8.4.1b13 → dcicutils-8.8.4.1b17}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: dcicutils
-Version: 8.8.4.1b13
+Version: 8.8.4.1b17
 Summary: Utility package for interacting with the 4DN Data Portal and other 4DN resources
 Home-page: https://github.com/4dn-dcic/utils
 License: MIT
@@ -26,8 +26,8 @@ Requires-Dist: PyJWT (>=2.6.0,<3.0.0)
 Requires-Dist: PyYAML (>=6.0.1,<7.0.0)
 Requires-Dist: appdirs (>=1.4.4,<2.0.0)
 Requires-Dist: aws-requests-auth (>=0.4.2,<1)
-Requires-Dist: boto3 (>=1.34.90,<2.0.0)
-Requires-Dist: botocore (>=1.34.90,<2.0.0)
+Requires-Dist: boto3 (>=1.34.93,<2.0.0)
+Requires-Dist: botocore (>=1.34.93,<2.0.0)
 Requires-Dist: chardet (>=5.2.0,<6.0.0)
 Requires-Dist: docker (>=4.4.4,<5.0.0)
 Requires-Dist: elasticsearch (==7.13.4)
@@ -43,6 +43,7 @@ Requires-Dist: pytz (>=2020.4)
 Requires-Dist: redis (>=4.5.1,<5.0.0)
 Requires-Dist: requests (>=2.21.0,<3.0.0)
 Requires-Dist: rfc3986 (>=1.4.0,<2.0.0)
+Requires-Dist: shortuuid (>=1.0.13,<2.0.0)
 Requires-Dist: structlog (>=19.2.0,<20.0.0)
 Requires-Dist: toml (>=0.10.1,<1)
 Requires-Dist: tqdm (>=4.66.2,<5.0.0)

{dcicutils-8.8.4.1b13 → dcicutils-8.8.4.1b17}/dcicutils/file_utils.py

@@ -1,4 +1,6 @@
 import glob
+import hashlib
+import io
 import os
 import pathlib
 from datetime import datetime
@@ -103,6 +105,76 @@ def are_files_equal(filea: str, fileb: str) -> bool:
         return False
 
 
+def compute_file_md5(file: str) -> str:
+    """
+    Returns the md5 checksum for the given file.
+    """
+    if not isinstance(file, str):
+        return ""
+    try:
+        md5 = hashlib.md5()
+        with open(file, "rb") as file:
+            for chunk in iter(lambda: file.read(4096), b""):
+                md5.update(chunk)
+        return md5.hexdigest()
+    except Exception:
+        return ""
+
+
+def compute_file_etag(file: str) -> Optional[str]:
+    """
+    Returns the AWS S3 "etag" for the given file; this value is md5-like but
+    not the same as a normal md5. We use this to compare that a file in S3
+    appears to be the exact the same file as a local file.
+    """
+    try:
+        with io.open(file, "rb") as f:
+            return _compute_file_etag(f)
+    except Exception:
+        return None
+
+
+def _compute_file_etag(f: io.BufferedReader) -> str:
+    # See: https://stackoverflow.com/questions/75723647/calculate-md5-from-aws-s3-etag
+    MULTIPART_THRESHOLD = 8388608
+    MULTIPART_CHUNKSIZE = 8388608
+    # BUFFER_SIZE = 1048576
+    # Verify some assumptions are correct
+    # assert(MULTIPART_CHUNKSIZE >= MULTIPART_THRESHOLD)
+    # assert((MULTIPART_THRESHOLD % BUFFER_SIZE) == 0)
+    # assert((MULTIPART_CHUNKSIZE % BUFFER_SIZE) == 0)
+    hash = hashlib.md5()
+    read = 0
+    chunks = None
+    while True:
+        # Read some from stdin, if we're at the end, stop reading
+        bits = f.read(1048576)
+        if len(bits) == 0:
+            break
+        read += len(bits)
+        hash.update(bits)
+        if chunks is None:
+            # We're handling a multi-part upload, so switch to calculating
+            # hashes of each chunk
+            if read >= MULTIPART_THRESHOLD:
+                chunks = b''
+        if chunks is not None:
+            if (read % MULTIPART_CHUNKSIZE) == 0:
+                # Dont with a chunk, add it to the list of hashes to hash later
+                chunks += hash.digest()
+                hash = hashlib.md5()
+    if chunks is None:
+        # Normal upload, just output the MD5 hash
+        etag = hash.hexdigest()
+    else:
+        # Multipart upload, need to output the hash of the hashes
+        if (read % MULTIPART_CHUNKSIZE) != 0:
+            # Add the last part if we have a partial chunk
+            chunks += hash.digest()
+        etag = hashlib.md5(chunks).hexdigest() + "-" + str(len(chunks) // 16)
+    return etag
+
+
 def create_random_file(file: Optional[str] = None, prefix: Optional[str] = None, suffix: Optional[str] = None,
                        nbytes: int = 1024, binary: bool = False, line_length: Optional[int] = None) -> str:
     """

{dcicutils-8.8.4.1b13 → dcicutils-8.8.4.1b17}/dcicutils/http_utils.py

@@ -1,20 +1,31 @@
 from contextlib import contextmanager
 import requests
-from typing import Optional
+from typing import Callable, Optional
 from dcicutils.tmpfile_utils import temporary_file
 
 
 @contextmanager
-def download(url: str, suffix: Optional[str] = None, binary: bool = True) -> Optional[str]:
+def download(url: str, suffix: Optional[str] = None, binary: bool = True,
+             progress: Optional[Callable] = None) -> Optional[str]:
     """
     Context manager to ownload the given URL into a temporary file and yields the file
     path to it. An optional file suffix may be specified. Defaults to binary file mode;
     if this is not desired then pass False as the binary argument.
     """
+    if not callable(progress):
+        progress = None
     with temporary_file(suffix=suffix) as file:
         response = requests.get(url, stream=True)
+        if progress:
+            nbytes = 0
+            nbytes_total = None
+            if isinstance(content_length := response.headers.get("Content-Length"), str) and content_length.isdigit():
+                nbytes_total = int(content_length)
         with open(file, "wb" if binary is True else "w") as f:
             for chunk in response.iter_content(chunk_size=8192):
                 if chunk:
                     f.write(chunk)
+                if progress:
+                    nbytes += len(chunk)
+                    progress(nbytes, nbytes_total)
         yield file

{dcicutils-8.8.4.1b13 → dcicutils-8.8.4.1b17}/dcicutils/misc_utils.py

@@ -19,6 +19,7 @@ import pytz
 import re
 import rfc3986.validators
 import rfc3986.exceptions
+import shortuuid
 import time
 import uuid
 import warnings
@@ -2698,3 +2699,9 @@ def get_cpu_architecture_name() -> str:
         if os_architecture_name == "x86_64": return "amd64"  # noqa
         return os_architecture_name
     return ""
+
+
+def short_uuid(length: Optional[int] = None):
+    if (length is None) or (not isinstance(length, int)) or (length < 1):
+        length = 16
+    return shortuuid.ShortUUID().random(length=length)

{dcicutils-8.8.4.1b13 → dcicutils-8.8.4.1b17}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "dcicutils"
-version = "8.8.4.1b13"  # TODO: To become 8.8.5
+version = "8.8.4.1b17"  # TODO: To become 8.8.5
 description = "Utility package for interacting with the 4DN Data Portal and other 4DN resources"
 authors = ["4DN-DCIC Team <support@4dnucleome.org>"]
 license = "MIT"
@@ -38,8 +38,8 @@ classifiers = [
 
 [tool.poetry.dependencies]
 python = ">=3.8,<3.13"
-boto3 = "^1.34.90"
-botocore = "^1.34.90"
+boto3 = "^1.34.93"
+botocore = "^1.34.93"
 # The DCIC portals (cgap-portal and fourfront) are very particular about which ElasticSearch version.
 # This value is intentionally pinned and must not be changed casually.
 elasticsearch = "7.13.4"
@@ -61,6 +61,7 @@ pyperclip = "^1.8.2"
 PyYAML = "^6.0.1"
 requests = "^2.21.0"
 rfc3986 = "^1.4.0"
+shortuuid = "^1.0.13"
 structlog = "^19.2.0"
 toml = ">=0.10.1,<1"
 tqdm = "^4.66.2"
@@ -70,8 +71,8 @@ webtest = "^2.0.34"
 
 
 [tool.poetry.dev-dependencies]
-boto3-stubs = "^1.34.90"
-botocore-stubs = "^1.34.90"
+boto3-stubs = "^1.34.93"
+botocore-stubs = "^1.34.93"
 coverage = ">=7.2.3"
 # Loaded manually in GA workflow for coverage because a dependency on 2to3
 # in its docopts dependency makes a problem for laoding it here in poetry. -kmp 7-Apr-2023