infra: get min versions (#27896)

.github/scripts/get_min_versions.py

@@ -7,12 +7,17 @@ else:
     # for python 3.10 and below, which doesnt have stdlib tomllib
     import tomli as tomllib
 
-from packaging.version import parse as parse_version
 from packaging.specifiers import SpecifierSet
 from packaging.version import Version
 
+
+import requests
+from packaging.version import parse
+from typing import List
+
 import re
 
+
 MIN_VERSION_LIBS = [
     "langchain-core",
     "langchain-community",
@@ -31,29 +36,61 @@ SKIP_IF_PULL_REQUEST = [
 ]
 
 
-def get_min_version(version: str) -> str:
-    # base regex for x.x.x with cases for rc/post/etc
-    # valid strings: https://peps.python.org/pep-0440/#public-version-identifiers
-    vstring = r"\d+(?:\.\d+){0,2}(?:(?:a|b|rc|\.post|\.dev)\d+)?"
-    # case ^x.x.x
-    _match = re.match(f"^\\^({vstring})$", version)
-    if _match:
-        return _match.group(1)
+def get_pypi_versions(package_name: str) -> List[str]:
+    """
+    Fetch all available versions for a package from PyPI.
 
-    # case >=x.x.x,<y.y.y
-    _match = re.match(f"^>=({vstring}),<({vstring})$", version)
-    if _match:
-        _min = _match.group(1)
-        _max = _match.group(2)
-        assert parse_version(_min) < parse_version(_max)
-        return _min
+    Args:
+        package_name (str): Name of the package
 
-    # case x.x.x
-    _match = re.match(f"^({vstring})$", version)
-    if _match:
-        return _match.group(1)
+    Returns:
+        List[str]: List of all available versions
 
-    raise ValueError(f"Unrecognized version format: {version}")
+    Raises:
+        requests.exceptions.RequestException: If PyPI API request fails
+        KeyError: If package not found or response format unexpected
+    """
+    pypi_url = f"https://pypi.org/pypi/{package_name}/json"
+    response = requests.get(pypi_url)
+    response.raise_for_status()
+    return list(response.json()["releases"].keys())
+
+
+def get_minimum_version(package_name: str, spec_string: str) -> Optional[str]:
+    """
+    Find the minimum published version that satisfies the given constraints.
+
+    Args:
+        package_name (str): Name of the package
+        spec_string (str): Version specification string (e.g., ">=0.2.43,<0.4.0,!=0.3.0")
+
+    Returns:
+        Optional[str]: Minimum compatible version or None if no compatible version found
+    """
+    # rewrite occurrences of ^0.0.z to 0.0.z (can be anywhere in constraint string)
+    spec_string = re.sub(r"\^0\.0\.(\d+)", r"0.0.\1", spec_string)
+    # rewrite occurrences of ^0.y.z to >=0.y.z,<0.y+1 (can be anywhere in constraint string)
+    for y in range(1, 10):
+        spec_string = re.sub(rf"\^0\.{y}\.(\d+)", rf">=0.{y}.\1,<0.{y+1}", spec_string)
+    # rewrite occurrences of ^x.y.z to >=x.y.z,<x+1.0.0 (can be anywhere in constraint string)
+    for x in range(1, 10):
+        spec_string = re.sub(
+            rf"\^{x}\.(\d+)\.(\d+)", rf">={x}.\1.\2,<{x+1}", spec_string
+        )
+
+    spec_set = SpecifierSet(spec_string)
+    all_versions = get_pypi_versions(package_name)
+
+    valid_versions = []
+    for version_str in all_versions:
+        try:
+            version = parse(version_str)
+            if spec_set.contains(version):
+                valid_versions.append(version)
+        except ValueError:
+            continue
+
+    return str(min(valid_versions)) if valid_versions else None
 
 
 def get_min_version_from_toml(
@@ -96,7 +133,7 @@ def get_min_version_from_toml(
                 ][0]["version"]
 
             # Use parse_version to get the minimum supported version from version_string
-            min_version = get_min_version(version_string)
+            min_version = get_minimum_version(lib, version_string)
 
             # Store the minimum version in the min_versions dictionary
             min_versions[lib] = min_version
@@ -112,6 +149,20 @@ def check_python_version(version_string, constraint_string):
     :param constraint_string: A string representing the package's Python version constraints (e.g. ">=3.6, <4.0").
     :return: True if the version matches the constraints, False otherwise.
     """
+
+    # rewrite occurrences of ^0.0.z to 0.0.z (can be anywhere in constraint string)
+    constraint_string = re.sub(r"\^0\.0\.(\d+)", r"0.0.\1", constraint_string)
+    # rewrite occurrences of ^0.y.z to >=0.y.z,<0.y+1.0 (can be anywhere in constraint string)
+    for y in range(1, 10):
+        constraint_string = re.sub(
+            rf"\^0\.{y}\.(\d+)", rf">=0.{y}.\1,<0.{y+1}.0", constraint_string
+        )
+    # rewrite occurrences of ^x.y.z to >=x.y.z,<x+1.0.0 (can be anywhere in constraint string)
+    for x in range(1, 10):
+        constraint_string = re.sub(
+            rf"\^{x}\.0\.(\d+)", rf">={x}.0.\1,<{x+1}.0.0", constraint_string
+        )
+
     try:
         version = Version(version_string)
         constraints = SpecifierSet(constraint_string)

.github/workflows/_release.yml

@@ -247,7 +247,7 @@ jobs:
         working-directory: ${{ inputs.working-directory }}
         id: min-version
         run: |
-          poetry run pip install packaging
+          poetry run pip install packaging requests
           python_version="$(poetry run python --version | awk '{print $2}')"
           min_versions="$(poetry run python $GITHUB_WORKSPACE/.github/scripts/get_min_versions.py pyproject.toml release $python_version)"
           echo "min-versions=$min_versions" >> "$GITHUB_OUTPUT"

.github/workflows/_test.yml

@@ -47,7 +47,7 @@ jobs:
         id: min-version
         shell: bash
         run: |
-          poetry run pip install packaging tomli
+          poetry run pip install packaging tomli requests
           python_version="$(poetry run python --version | awk '{print $2}')"
           min_versions="$(poetry run python $GITHUB_WORKSPACE/.github/scripts/get_min_versions.py pyproject.toml pull_request $python_version)"
           echo "min-versions=$min_versions" >> "$GITHUB_OUTPUT"

.github/workflows/check_diffs.yml

@@ -31,7 +31,7 @@ jobs:
         uses: Ana06/get-changed-files@v2.2.0
       - id: set-matrix
         run: |
-          python -m pip install packaging
+          python -m pip install packaging requests
           python .github/scripts/check_diff.py ${{ steps.files.outputs.all }} >> $GITHUB_OUTPUT
     outputs:
       lint: ${{ steps.set-matrix.outputs.lint }}