_version.py

# This file helps to compute a version number in source trees obtained from
# git-archive tarball (such as those provided by githubs download-from-tag
# feature). Distribution tarballs (built by setup.py sdist) and build
# directories (produced by setup.py build) will contain a much shorter file
# that just contains the computed version number.

# This file is released into the public domain.
# Generated by versioneer-0.29
# https://github.com/python-versioneer/python-versioneer

"""Git implementation of _version.py."""

import errno
import functools
import os
import re
import subprocess
import sys
from typing import Any, Callable, Dict, List, Optional, Tuple

import versioneer

hardcoded_version = None


def get_current_version():
    if hardcoded_version is not None:
        return hardcoded_version
    return versioneer.get_version()


def get_keywords() -> Dict[str, str]:
    """Get the keywords needed to look up the version information."""
    # these strings will be replaced by git during git-archive.
    # setup.py/versioneer.py will grep for the variable names, so they must
    # each be defined on a line of their own. _version.py will just call
    # get_keywords().
    git_refnames = "$Format:%d$"
    git_full = "$Format:%H$"
    git_date = "$Format:%ci$"
    keywords = {"refnames": git_refnames, "full": git_full, "date": git_date}
    return keywords


class VersioneerConfig:
    """Container for Versioneer configuration parameters."""

    VCS: str
    style: str
    tag_prefix: str
    parentdir_prefix: str
    versionfile_source: str
    verbose: bool


def get_config() -> VersioneerConfig:
    """Create, populate and return the VersioneerConfig() object."""
    # these strings are filled in when 'setup.py versioneer' creates
    # _version.py
    cfg = VersioneerConfig()
    cfg.VCS = "git"
    cfg.style = "pep440"
    cfg.tag_prefix = ""
    cfg.parentdir_prefix = ""
    cfg.versionfile_source = "src/unitxt/_version.py"
    cfg.verbose = False
    return cfg


class NotThisMethod(Exception):
    """Exception raised if a method is not valid for the current scenario."""


LONG_VERSION_PY: Dict[str, str] = {}
HANDLERS: Dict[str, Dict[str, Callable]] = {}


def register_vcs_handler(vcs: str, method: str) -> Callable:  # decorator
    """Create decorator to mark a method as the handler of a VCS."""

    def decorate(f: Callable) -> Callable:
        """Store f in HANDLERS[vcs][method]."""
        if vcs not in HANDLERS:
            HANDLERS[vcs] = {}
        HANDLERS[vcs][method] = f
        return f

    return decorate


def run_command(
    commands: List[str],
    args: List[str],
    cwd: Optional[str] = None,
    verbose: bool = False,
    hide_stderr: bool = False,
    env: Optional[Dict[str, str]] = None,
) -> Tuple[Optional[str], Optional[int]]:
    """Call the given command(s)."""
    assert isinstance(commands, list)
    process = None

    popen_kwargs: Dict[str, Any] = {}
    if sys.platform == "win32":
        # This hides the console window if pythonw.exe is used
        startupinfo = subprocess.STARTUPINFO()
        startupinfo.dwFlags |= subprocess.STARTF_USESHOWWINDOW
        popen_kwargs["startupinfo"] = startupinfo

    for command in commands:
        try:
            dispcmd = str([command] + args)
            # remember shell=False, so use git.cmd on windows, not just git
            process = subprocess.Popen(
                [command] + args,
                cwd=cwd,
                env=env,
                stdout=subprocess.PIPE,
                stderr=(subprocess.PIPE if hide_stderr else None),
                **popen_kwargs,
            )
            break
        except OSError as e:
            if e.errno == errno.ENOENT:
                continue
            if verbose:
                print("unable to run %s" % dispcmd)
                print(e)
            return None, None
    else:
        if verbose:
            print("unable to find command, tried %s" % (commands,))
        return None, None
    stdout = process.communicate()[0].strip().decode()
    if process.returncode != 0:
        if verbose:
            print("unable to run %s (error)" % dispcmd)
            print("stdout was %s" % stdout)
        return None, process.returncode
    return stdout, process.returncode


def versions_from_parentdir(
    parentdir_prefix: str,
    root: str,
    verbose: bool,
) -> Dict[str, Any]:
    """Try to determine the version from the parent directory name.

    Source tarballs conventionally unpack into a directory that includes both
    the project name and a version string. We will also support searching up
    two directory levels for an appropriately named parent directory
    """
    rootdirs = []

    for _ in range(3):
        dirname = os.path.basename(root)
        if dirname.startswith(parentdir_prefix):
            return {
                "version": dirname[len(parentdir_prefix) :],
                "full-revisionid": None,
                "dirty": False,
                "error": None,
                "date": None,
            }
        rootdirs.append(root)
        root = os.path.dirname(root)  # up a level

    if verbose:
        print("Tried directories %s but none started with prefix %s" % (str(rootdirs), parentdir_prefix))
    raise NotThisMethod("rootdir doesn't start with parentdir_prefix")


@register_vcs_handler("git", "get_keywords")
def git_get_keywords(versionfile_abs: str) -> Dict[str, str]:
    """Extract version information from the given file."""
    # the code embedded in _version.py can just fetch the value of these
    # keywords. When used from setup.py, we don't want to import _version.py,
    # so we do it with a regexp instead. This function is not used from
    # _version.py.
    keywords: Dict[str, str] = {}
    try:
        with open(versionfile_abs, "r") as fobj:
            for line in fobj:
                if line.strip().startswith("git_refnames ="):
                    mo = re.search(r'=\s*"(.*)"', line)
                    if mo:
                        keywords["refnames"] = mo.group(1)
                if line.strip().startswith("git_full ="):
                    mo = re.search(r'=\s*"(.*)"', line)
                    if mo:
                        keywords["full"] = mo.group(1)
                if line.strip().startswith("git_date ="):
                    mo = re.search(r'=\s*"(.*)"', line)
                    if mo:
                        keywords["date"] = mo.group(1)
    except OSError:
        pass
    return keywords


@register_vcs_handler("git", "keywords")
def git_versions_from_keywords(
    keywords: Dict[str, str],
    tag_prefix: str,
    verbose: bool,
) -> Dict[str, Any]:
    """Get version information from git keywords."""
    if "refnames" not in keywords:
        raise NotThisMethod("Short version file found")
    date = keywords.get("date")
    if date is not None:
        # Use only the last line.  Previous lines may contain GPG signature
        # information.
        date = date.splitlines()[-1]

        # git-2.2.0 added "%cI", which expands to an ISO-8601 -compliant
        # datestamp. However we prefer "%ci" (which expands to an "ISO-8601
        # -like" string, which we must then edit to make compliant), because
        # it's been around since git-1.5.3, and it's too difficult to
        # discover which version we're using, or to work around using an
        # older one.
        date = date.strip().replace(" ", "T", 1).replace(" ", "", 1)
    refnames = keywords["refnames"].strip()
    if refnames.startswith("$Format"):
        if verbose:
            print("keywords are unexpanded, not using")
        raise NotThisMethod("unexpanded keywords, not a git-archive tarball")
    refs = {r.strip() for r in refnames.strip("()").split(",")}
    # starting in git-1.8.3, tags are listed as "tag: foo-1.0" instead of
    # just "foo-1.0". If we see a "tag: " prefix, prefer those.
    TAG = "tag: "
    tags = {r[len(TAG) :] for r in refs if r.startswith(TAG)}
    if not tags:
        # Either we're using git < 1.8.3, or there really are no tags. We use
        # a heuristic: assume all version tags have a digit. The old git %d
        # expansion behaves like git log --decorate=short and strips out the
        # refs/heads/ and refs/tags/ prefixes that would let us distinguish
        # between branches and tags. By ignoring refnames without digits, we
        # filter out many common branch names like "release" and
        # "stabilization", as well as "HEAD" and "master".
        tags = {r for r in refs if re.search(r"\d", r)}
        if verbose:
            print("discarding '%s', no digits" % ",".join(refs - tags))
    if verbose:
        print("likely tags: %s" % ",".join(sorted(tags)))
    for ref in sorted(tags):
        # sorting will prefer e.g. "2.0" over "2.0rc1"
        if ref.startswith(tag_prefix):
            r = ref[len(tag_prefix) :]
            # Filter out refs that exactly match prefix or that don't start
            # with a number once the prefix is stripped (mostly a concern
            # when prefix is '')
            if not re.match(r"\d", r):
                continue
            if verbose:
                print("picking %s" % r)
            return {
                "version": r,
                "full-revisionid": keywords["full"].strip(),
                "dirty": False,
                "error": None,
                "date": date,
            }
    # no suitable tags, so version is "0+unknown", but full hex is still there
    if verbose:
        print("no suitable tags, using unknown + full revision id")
    return {
        "version": "0+unknown",
        "full-revisionid": keywords["full"].strip(),
        "dirty": False,
        "error": "no suitable tags",
        "date": None,
    }


@register_vcs_handler("git", "pieces_from_vcs")
def git_pieces_from_vcs(tag_prefix: str, root: str, verbose: bool, runner: Callable = run_command) -> Dict[str, Any]:
    """Get version from 'git describe' in the root of the source tree.

    This only gets called if the git-archive 'subst' keywords were *not*
    expanded, and _version.py hasn't already been rewritten with a short
    version string, meaning we're inside a checked out source tree.
    """
    GITS = ["git"]
    if sys.platform == "win32":
        GITS = ["git.cmd", "git.exe"]

    # GIT_DIR can interfere with correct operation of Versioneer.
    # It may be intended to be passed to the Versioneer-versioned project,
    # but that should not change where we get our version from.
    env = os.environ.copy()
    env.pop("GIT_DIR", None)
    runner = functools.partial(runner, env=env)

    _, rc = runner(GITS, ["rev-parse", "--git-dir"], cwd=root, hide_stderr=not verbose)
    if rc != 0:
        if verbose:
            print("Directory %s not under git control" % root)
        raise NotThisMethod("'git rev-parse --git-dir' returned error")

    # if there is a tag matching tag_prefix, this yields TAG-NUM-gHEX[-dirty]
    # if there isn't one, this yields HEX[-dirty] (no NUM)
    describe_out, rc = runner(
        GITS, ["describe", "--tags", "--dirty", "--always", "--long", "--match", f"{tag_prefix}[[:digit:]]*"], cwd=root
    )
    # --long was added in git-1.5.5
    if describe_out is None:
        raise NotThisMethod("'git describe' failed")
    describe_out = describe_out.strip()
    full_out, rc = runner(GITS, ["rev-parse", "HEAD"], cwd=root)
    if full_out is None:
        raise NotThisMethod("'git rev-parse' failed")
    full_out = full_out.strip()

    pieces: Dict[str, Any] = {}
    pieces["long"] = full_out
    pieces["short"] = full_out[:7]  # maybe improved later
    pieces["error"] = None

    branch_name, rc = runner(GITS, ["rev-parse", "--abbrev-ref", "HEAD"], cwd=root)
    # --abbrev-ref was added in git-1.6.3
    if rc != 0 or branch_name is None:
        raise NotThisMethod("'git rev-parse --abbrev-ref' returned error")
    branch_name = branch_name.strip()

    if branch_name == "HEAD":
        # If we aren't exactly on a branch, pick a branch which represents
        # the current commit. If all else fails, we are on a branchless
        # commit.
        branches, rc = runner(GITS, ["branch", "--contains"], cwd=root)
        # --contains was added in git-1.5.4
        if rc != 0 or branches is None:
            raise NotThisMethod("'git branch --contains' returned error")
        branches = branches.split("\n")

        # Remove the first line if we're running detached
        if "(" in branches[0]:
            branches.pop(0)

        # Strip off the leading "* " from the list of branches.
        branches = [branch[2:] for branch in branches]
        if "master" in branches:
            branch_name = "master"
        elif not branches:
            branch_name = None
        else:
            # Pick the first branch that is returned. Good or bad.
            branch_name = branches[0]

    pieces["branch"] = branch_name

    # parse describe_out. It will be like TAG-NUM-gHEX[-dirty] or HEX[-dirty]
    # TAG might have hyphens.
    git_describe = describe_out

    # look for -dirty suffix
    dirty = git_describe.endswith("-dirty")
    pieces["dirty"] = dirty
    if dirty:
        git_describe = git_describe[: git_describe.rindex("-dirty")]

    # now we have TAG-NUM-gHEX or HEX

    if "-" in git_describe:
        # TAG-NUM-gHEX
        mo = re.search(r"^(.+)-(\d+)-g([0-9a-f]+)$", git_describe)
        if not mo:
            # unparsable. Maybe git-describe is misbehaving?
            pieces["error"] = "unable to parse git-describe output: '%s'" % describe_out
            return pieces

        # tag
        full_tag = mo.group(1)
        if not full_tag.startswith(tag_prefix):
            if verbose:
                fmt = "tag '%s' doesn't start with prefix '%s'"
                print(fmt % (full_tag, tag_prefix))
            pieces["error"] = "tag '%s' doesn't start with prefix '%s'" % (full_tag, tag_prefix)
            return pieces
        pieces["closest-tag"] = full_tag[len(tag_prefix) :]

        # distance: number of commits since tag
        pieces["distance"] = int(mo.group(2))

        # commit: short hex revision ID
        pieces["short"] = mo.group(3)

    else:
        # HEX: no tags
        pieces["closest-tag"] = None
        out, rc = runner(GITS, ["rev-list", "HEAD", "--left-right"], cwd=root)
        pieces["distance"] = len(out.split())  # total number of commits

    # commit date: see ISO-8601 comment in git_versions_from_keywords()
    date = runner(GITS, ["show", "-s", "--format=%ci", "HEAD"], cwd=root)[0].strip()
    # Use only the last line.  Previous lines may contain GPG signature
    # information.
    date = date.splitlines()[-1]
    pieces["date"] = date.strip().replace(" ", "T", 1).replace(" ", "", 1)

    return pieces


def plus_or_dot(pieces: Dict[str, Any]) -> str:
    """Return a + if we don't already have one, else return a ."""
    if "+" in pieces.get("closest-tag", ""):
        return "."
    return "+"


def render_pep440(pieces: Dict[str, Any]) -> str:
    """Build up version string, with post-release "local version identifier".

    Our goal: TAG[+DISTANCE.gHEX[.dirty]] . Note that if you
    get a tagged build and then dirty it, you'll get TAG+0.gHEX.dirty

    Exceptions:
    1: no tags. git_describe was just HEX. 0+untagged.DISTANCE.gHEX[.dirty]
    """
    if pieces["closest-tag"]:
        rendered = pieces["closest-tag"]
        if pieces["distance"] or pieces["dirty"]:
            rendered += plus_or_dot(pieces)
            rendered += "%d.g%s" % (pieces["distance"], pieces["short"])
            if pieces["dirty"]:
                rendered += ".dirty"
    else:
        # exception #1
        rendered = "0+untagged.%d.g%s" % (pieces["distance"], pieces["short"])
        if pieces["dirty"]:
            rendered += ".dirty"
    return rendered


def render_pep440_branch(pieces: Dict[str, Any]) -> str:
    """TAG[[.dev0]+DISTANCE.gHEX[.dirty]] .

    The ".dev0" means not master branch. Note that .dev0 sorts backwards
    (a feature branch will appear "older" than the master branch).

    Exceptions:
    1: no tags. 0[.dev0]+untagged.DISTANCE.gHEX[.dirty]
    """
    if pieces["closest-tag"]:
        rendered = pieces["closest-tag"]
        if pieces["distance"] or pieces["dirty"]:
            if pieces["branch"] != "master":
                rendered += ".dev0"
            rendered += plus_or_dot(pieces)
            rendered += "%d.g%s" % (pieces["distance"], pieces["short"])
            if pieces["dirty"]:
                rendered += ".dirty"
    else:
        # exception #1
        rendered = "0"
        if pieces["branch"] != "master":
            rendered += ".dev0"
        rendered += "+untagged.%d.g%s" % (pieces["distance"], pieces["short"])
        if pieces["dirty"]:
            rendered += ".dirty"
    return rendered


def pep440_split_post(ver: str) -> Tuple[str, Optional[int]]:
    """Split pep440 version string at the post-release segment.

    Returns the release segments before the post-release and the
    post-release version number (or -1 if no post-release segment is present).
    """
    vc = str.split(ver, ".post")
    return vc[0], int(vc[1] or 0) if len(vc) == 2 else None


def render_pep440_pre(pieces: Dict[str, Any]) -> str:
    """TAG[.postN.devDISTANCE] -- No -dirty.

    Exceptions:
    1: no tags. 0.post0.devDISTANCE
    """
    if pieces["closest-tag"]:
        if pieces["distance"]:
            # update the post release segment
            tag_version, post_version = pep440_split_post(pieces["closest-tag"])
            rendered = tag_version
            if post_version is not None:
                rendered += ".post%d.dev%d" % (post_version + 1, pieces["distance"])
            else:
                rendered += ".post0.dev%d" % (pieces["distance"])
        else:
            # no commits, use the tag as the version
            rendered = pieces["closest-tag"]
    else:
        # exception #1
        rendered = "0.post0.dev%d" % pieces["distance"]
    return rendered


def render_pep440_post(pieces: Dict[str, Any]) -> str:
    """TAG[.postDISTANCE[.dev0]+gHEX] .

    The ".dev0" means dirty. Note that .dev0 sorts backwards
    (a dirty tree will appear "older" than the corresponding clean one),
    but you shouldn't be releasing software with -dirty anyways.

    Exceptions:
    1: no tags. 0.postDISTANCE[.dev0]
    """
    if pieces["closest-tag"]:
        rendered = pieces["closest-tag"]
        if pieces["distance"] or pieces["dirty"]:
            rendered += ".post%d" % pieces["distance"]
            if pieces["dirty"]:
                rendered += ".dev0"
            rendered += plus_or_dot(pieces)
            rendered += "g%s" % pieces["short"]
    else:
        # exception #1
        rendered = "0.post%d" % pieces["distance"]
        if pieces["dirty"]:
            rendered += ".dev0"
        rendered += "+g%s" % pieces["short"]
    return rendered


def render_pep440_post_branch(pieces: Dict[str, Any]) -> str:
    """TAG[.postDISTANCE[.dev0]+gHEX[.dirty]] .

    The ".dev0" means not master branch.

    Exceptions:
    1: no tags. 0.postDISTANCE[.dev0]+gHEX[.dirty]
    """
    if pieces["closest-tag"]:
        rendered = pieces["closest-tag"]
        if pieces["distance"] or pieces["dirty"]:
            rendered += ".post%d" % pieces["distance"]
            if pieces["branch"] != "master":
                rendered += ".dev0"
            rendered += plus_or_dot(pieces)
            rendered += "g%s" % pieces["short"]
            if pieces["dirty"]:
                rendered += ".dirty"
    else:
        # exception #1
        rendered = "0.post%d" % pieces["distance"]
        if pieces["branch"] != "master":
            rendered += ".dev0"
        rendered += "+g%s" % pieces["short"]
        if pieces["dirty"]:
            rendered += ".dirty"
    return rendered


def render_pep440_old(pieces: Dict[str, Any]) -> str:
    """TAG[.postDISTANCE[.dev0]] .

    The ".dev0" means dirty.

    Exceptions:
    1: no tags. 0.postDISTANCE[.dev0]
    """
    if pieces["closest-tag"]:
        rendered = pieces["closest-tag"]
        if pieces["distance"] or pieces["dirty"]:
            rendered += ".post%d" % pieces["distance"]
            if pieces["dirty"]:
                rendered += ".dev0"
    else:
        # exception #1
        rendered = "0.post%d" % pieces["distance"]
        if pieces["dirty"]:
            rendered += ".dev0"
    return rendered


def render_git_describe(pieces: Dict[str, Any]) -> str:
    """TAG[-DISTANCE-gHEX][-dirty].

    Like 'git describe --tags --dirty --always'.

    Exceptions:
    1: no tags. HEX[-dirty]  (note: no 'g' prefix)
    """
    if pieces["closest-tag"]:
        rendered = pieces["closest-tag"]
        if pieces["distance"]:
            rendered += "-%d-g%s" % (pieces["distance"], pieces["short"])
    else:
        # exception #1
        rendered = pieces["short"]
    if pieces["dirty"]:
        rendered += "-dirty"
    return rendered


def render_git_describe_long(pieces: Dict[str, Any]) -> str:
    """TAG-DISTANCE-gHEX[-dirty].

    Like 'git describe --tags --dirty --always -long'.
    The distance/hash is unconditional.

    Exceptions:
    1: no tags. HEX[-dirty]  (note: no 'g' prefix)
    """
    if pieces["closest-tag"]:
        rendered = pieces["closest-tag"]
        rendered += "-%d-g%s" % (pieces["distance"], pieces["short"])
    else:
        # exception #1
        rendered = pieces["short"]
    if pieces["dirty"]:
        rendered += "-dirty"
    return rendered


def render(pieces: Dict[str, Any], style: str) -> Dict[str, Any]:
    """Render the given version pieces into the requested style."""
    if pieces["error"]:
        return {
            "version": "unknown",
            "full-revisionid": pieces.get("long"),
            "dirty": None,
            "error": pieces["error"],
            "date": None,
        }

    if not style or style == "default":
        style = "pep440"  # the default

    if style == "pep440":
        rendered = render_pep440(pieces)
    elif style == "pep440-branch":
        rendered = render_pep440_branch(pieces)
    elif style == "pep440-pre":
        rendered = render_pep440_pre(pieces)
    elif style == "pep440-post":
        rendered = render_pep440_post(pieces)
    elif style == "pep440-post-branch":
        rendered = render_pep440_post_branch(pieces)
    elif style == "pep440-old":
        rendered = render_pep440_old(pieces)
    elif style == "git-describe":
        rendered = render_git_describe(pieces)
    elif style == "git-describe-long":
        rendered = render_git_describe_long(pieces)
    else:
        raise ValueError("unknown style '%s'" % style)

    return {
        "version": rendered,
        "full-revisionid": pieces["long"],
        "dirty": pieces["dirty"],
        "error": None,
        "date": pieces.get("date"),
    }


def get_versions() -> Dict[str, Any]:
    """Get version information or return default if unable to do so."""
    # I am in _version.py, which lives at ROOT/VERSIONFILE_SOURCE. If we have
    # __file__, we can work backwards from there to the root. Some
    # py2exe/bbfreeze/non-CPython implementations don't do __file__, in which
    # case we can only use expanded keywords.

    cfg = get_config()
    verbose = cfg.verbose

    try:
        return git_versions_from_keywords(get_keywords(), cfg.tag_prefix, verbose)
    except NotThisMethod:
        pass

    try:
        root = os.path.realpath(__file__)
        # versionfile_source is the relative path from the top of the source
        # tree (where the .git directory might live) to this file. Invert
        # this to find the root from __file__.
        for _ in cfg.versionfile_source.split("/"):
            root = os.path.dirname(root)
    except NameError:
        return {
            "version": "0+unknown",
            "full-revisionid": None,
            "dirty": None,
            "error": "unable to find root of source tree",
            "date": None,
        }

    try:
        pieces = git_pieces_from_vcs(cfg.tag_prefix, root, verbose)
        return render(pieces, cfg.style)
    except NotThisMethod:
        pass

    try:
        if cfg.parentdir_prefix:
            return versions_from_parentdir(cfg.parentdir_prefix, root, verbose)
    except NotThisMethod:
        pass

    return {
        "version": "0+unknown",
        "full-revisionid": None,
        "dirty": None,
        "error": "unable to compute version",
        "date": None,
    }