github/langchain
1
0
Fork 0
mirror of https://github.com/hwchase17/langchain.git synced 2025-09-06 21:43:44 +00:00
Code Issues Packages Projects Releases Wiki Activity

chore: formatting across codebase (#32466)

Browse Source
This commit is contained in:
Mason Daugherty
2025-08-08 10:20:10 -04:00
committed by GitHub
parent 02001212b0
commit c31236264e
60 changed files with 635 additions and 369 deletions
Download Patch File Download Diff File Expand all files Collapse all files

416
.github/tools/git-restore-mtime vendored
View File

@@ -81,56 +81,93 @@ import time
__version__ = "2022.12+dev"
# Update symlinks only if the platform supports not following them
UPDATE_SYMLINKS = bool(os.utime in getattr(os, 'supports_follow_symlinks', []))
UPDATE_SYMLINKS = bool(os.utime in getattr(os, "supports_follow_symlinks", []))
# Call os.path.normpath() only if not in a POSIX platform (Windows)
NORMALIZE_PATHS = (os.path.sep != '/')
NORMALIZE_PATHS = os.path.sep != "/"
# How many files to process in each batch when re-trying merge commits
STEPMISSING = 100
# (Extra) keywords for the os.utime() call performed by touch()
UTIME_KWS = {} if not UPDATE_SYMLINKS else {'follow_symlinks': False}
UTIME_KWS = {} if not UPDATE_SYMLINKS else {"follow_symlinks": False}
# Command-line interface ######################################################
def parse_args():
parser = argparse.ArgumentParser(
description=__doc__.split('\n---')[0])
parser = argparse.ArgumentParser(description=__doc__.split("\n---")[0])
group = parser.add_mutually_exclusive_group()
group.add_argument('--quiet', '-q', dest='loglevel',
action="store_const", const=logging.WARNING, default=logging.INFO,
help="Suppress informative messages and summary statistics.")
group.add_argument('--verbose', '-v', action="count", help="""
group.add_argument(
"--quiet",
"-q",
dest="loglevel",
action="store_const",
const=logging.WARNING,
default=logging.INFO,
help="Suppress informative messages and summary statistics.",
)
group.add_argument(
"--verbose",
"-v",
action="count",
help="""
Print additional information for each processed file.
Specify twice to further increase verbosity.
""")
""",
)
parser.add_argument('--cwd', '-C', metavar="DIRECTORY", help="""
parser.add_argument(
"--cwd",
"-C",
metavar="DIRECTORY",
help="""
Run as if %(prog)s was started in directory %(metavar)s.
This affects how --work-tree, --git-dir and PATHSPEC arguments are handled.
See 'man 1 git' or 'git --help' for more information.
""")
""",
)
parser.add_argument('--git-dir', dest='gitdir', metavar="GITDIR", help="""
parser.add_argument(
"--git-dir",
dest="gitdir",
metavar="GITDIR",
help="""
Path to the git repository, by default auto-discovered by searching
the current directory and its parents for a .git/ subdirectory.
""")
""",
)
parser.add_argument('--work-tree', dest='workdir', metavar="WORKTREE", help="""
parser.add_argument(
"--work-tree",
dest="workdir",
metavar="WORKTREE",
help="""
Path to the work tree root, by default the parent of GITDIR if it's
automatically discovered, or the current directory if GITDIR is set.
""")
""",
)
parser.add_argument('--force', '-f', default=False, action="store_true", help="""
parser.add_argument(
"--force",
"-f",
default=False,
action="store_true",
help="""
Force updating files with uncommitted modifications.
Untracked files and uncommitted deletions, renames and additions are
always ignored.
""")
""",
)
parser.add_argument('--merge', '-m', default=False, action="store_true", help="""
parser.add_argument(
"--merge",
"-m",
default=False,
action="store_true",
help="""
Include merge commits.
Leads to more recent times and more files per commit, thus with the same
time, which may or may not be what you want.
@@ -138,71 +175,130 @@ def parse_args():
are found sooner, which can improve performance, sometimes substantially.
But as merge commits are usually huge, processing them may also take longer.
By default, merge commits are only used for files missing from regular commits.
""")
""",
)
parser.add_argument('--first-parent', default=False, action="store_true", help="""
parser.add_argument(
"--first-parent",
default=False,
action="store_true",
help="""
Consider only the first parent, the "main branch", when evaluating merge commits.
Only effective when merge commits are processed, either when --merge is
used or when finding missing files after the first regular log search.
See --skip-missing.
""")
""",
)
parser.add_argument('--skip-missing', '-s', dest="missing", default=True,
action="store_false", help="""
parser.add_argument(
"--skip-missing",
"-s",
dest="missing",
default=True,
action="store_false",
help="""
Do not try to find missing files.
If merge commits were not evaluated with --merge and some files were
not found in regular commits, by default %(prog)s searches for these
files again in the merge commits.
This option disables this retry, so files found only in merge commits
will not have their timestamp updated.
""")
""",
)
parser.add_argument('--no-directories', '-D', dest='dirs', default=True,
action="store_false", help="""
parser.add_argument(
"--no-directories",
"-D",
dest="dirs",
default=True,
action="store_false",
help="""
Do not update directory timestamps.
By default, use the time of its most recently created, renamed or deleted file.
Note that just modifying a file will NOT update its directory time.
""")
""",
)
parser.add_argument('--test', '-t', default=False, action="store_true",
help="Test run: do not actually update any file timestamp.")
parser.add_argument(
"--test",
"-t",
default=False,
action="store_true",
help="Test run: do not actually update any file timestamp.",
)
parser.add_argument('--commit-time', '-c', dest='commit_time', default=False,
action='store_true', help="Use commit time instead of author time.")
parser.add_argument(
"--commit-time",
"-c",
dest="commit_time",
default=False,
action="store_true",
help="Use commit time instead of author time.",
)
parser.add_argument('--oldest-time', '-o', dest='reverse_order', default=False,
action='store_true', help="""
parser.add_argument(
"--oldest-time",
"-o",
dest="reverse_order",
default=False,
action="store_true",
help="""
Update times based on the oldest, instead of the most recent commit of a file.
This reverses the order in which the git log is processed to emulate a
file "creation" date. Note this will be inaccurate for files deleted and
re-created at later dates.
""")
""",
)
parser.add_argument('--skip-older-than', metavar='SECONDS', type=int, help="""
parser.add_argument(
"--skip-older-than",
metavar="SECONDS",
type=int,
help="""
Ignore files that are currently older than %(metavar)s.
Useful in workflows that assume such files already have a correct timestamp,
as it may improve performance by processing fewer files.
""")
""",
)
parser.add_argument('--skip-older-than-commit', '-N', default=False,
action='store_true', help="""
parser.add_argument(
"--skip-older-than-commit",
"-N",
default=False,
action="store_true",
help="""
Ignore files older than the timestamp it would be updated to.
Such files may be considered "original", likely in the author's repository.
""")
""",
)
parser.add_argument('--unique-times', default=False, action="store_true", help="""
parser.add_argument(
"--unique-times",
default=False,
action="store_true",
help="""
Set the microseconds to a unique value per commit.
Allows telling apart changes that would otherwise have identical timestamps,
as git's time accuracy is in seconds.
""")
""",
)
parser.add_argument('pathspec', nargs='*', metavar='PATHSPEC', help="""
parser.add_argument(
"pathspec",
nargs="*",
metavar="PATHSPEC",
help="""
Only modify paths matching %(metavar)s, relative to current directory.
By default, update all but untracked files and submodules.
""")
""",
)
parser.add_argument('--version', '-V', action='version',
version='%(prog)s version {version}'.format(version=get_version()))
parser.add_argument(
"--version",
"-V",
action="version",
version="%(prog)s version {version}".format(version=get_version()),
)
args_ = parser.parse_args()
if args_.verbose:
@@ -212,17 +308,18 @@ def parse_args():
def get_version(version=__version__):
if not version.endswith('+dev'):
if not version.endswith("+dev"):
return version
try:
cwd = os.path.dirname(os.path.realpath(__file__))
return Git(cwd=cwd, errors=False).describe().lstrip('v')
return Git(cwd=cwd, errors=False).describe().lstrip("v")
except Git.Error:
return '-'.join((version, "unknown"))
return "-".join((version, "unknown"))
# Helper functions ############################################################
def setup_logging():
"""Add TRACE logging level and corresponding method, return the root logger"""
logging.TRACE = TRACE = logging.DEBUG // 2
@@ -255,11 +352,13 @@ def normalize(path):
if path and path[0] == '"':
# Python 2: path = path[1:-1].decode("string-escape")
# Python 3: https://stackoverflow.com/a/46650050/624066
path = (path[1:-1] # Remove enclosing double quotes
.encode('latin1') # Convert to bytes, required by 'unicode-escape'
.decode('unicode-escape') # Perform the actual octal-escaping decode
.encode('latin1') # 1:1 mapping to bytes, UTF-8 encoded
.decode('utf8', 'surrogateescape')) # Decode from UTF-8
path = (
path[1:-1] # Remove enclosing double quotes
.encode("latin1") # Convert to bytes, required by 'unicode-escape'
.decode("unicode-escape") # Perform the actual octal-escaping decode
.encode("latin1") # 1:1 mapping to bytes, UTF-8 encoded
.decode("utf8", "surrogateescape")
) # Decode from UTF-8
if NORMALIZE_PATHS:
# Make sure the slash matches the OS; for Windows we need a backslash
path = os.path.normpath(path)
@@ -282,12 +381,12 @@ def touch_ns(path, mtime_ns):
def isodate(secs: int):
# time.localtime() accepts floats, but discards fractional part
return time.strftime('%Y-%m-%d %H:%M:%S', time.localtime(secs))
return time.strftime("%Y-%m-%d %H:%M:%S", time.localtime(secs))
def isodate_ns(ns: int):
# for integers fromtimestamp() is equivalent and ~16% slower than isodate()
return datetime.datetime.fromtimestamp(ns / 1000000000).isoformat(sep=' ')
return datetime.datetime.fromtimestamp(ns / 1000000000).isoformat(sep=" ")
def get_mtime_ns(secs: int, idx: int):
@@ -305,35 +404,49 @@ def get_mtime_path(path):
# Git class and parse_log(), the heart of the script ##########################
class Git:
def __init__(self, workdir=None, gitdir=None, cwd=None, errors=True):
self.gitcmd = ['git']
self.gitcmd = ["git"]
self.errors = errors
self._proc = None
if workdir: self.gitcmd.extend(('--work-tree', workdir))
if gitdir: self.gitcmd.extend(('--git-dir', gitdir))
if cwd: self.gitcmd.extend(('-C', cwd))
if workdir:
self.gitcmd.extend(("--work-tree", workdir))
if gitdir:
self.gitcmd.extend(("--git-dir", gitdir))
if cwd:
self.gitcmd.extend(("-C", cwd))
self.workdir, self.gitdir = self._get_repo_dirs()
def ls_files(self, paths: list = None):
return (normalize(_) for _ in self._run('ls-files --full-name', paths))
return (normalize(_) for _ in self._run("ls-files --full-name", paths))
def ls_dirty(self, force=False):
return (normalize(_[3:].split(' -> ', 1)[-1])
for _ in self._run('status --porcelain')
if _[:2] != '??' and (not force or (_[0] in ('R', 'A')
or _[1] == 'D')))
return (
normalize(_[3:].split(" -> ", 1)[-1])
for _ in self._run("status --porcelain")
if _[:2] != "??" and (not force or (_[0] in ("R", "A") or _[1] == "D"))
)
def log(self, merge=False, first_parent=False, commit_time=False,
reverse_order=False, paths: list = None):
cmd = 'whatchanged --pretty={}'.format('%ct' if commit_time else '%at')
if merge: cmd += ' -m'
if first_parent: cmd += ' --first-parent'
if reverse_order: cmd += ' --reverse'
def log(
self,
merge=False,
first_parent=False,
commit_time=False,
reverse_order=False,
paths: list = None,
):
cmd = "whatchanged --pretty={}".format("%ct" if commit_time else "%at")
if merge:
cmd += " -m"
if first_parent:
cmd += " --first-parent"
if reverse_order:
cmd += " --reverse"
return self._run(cmd, paths)
def describe(self):
return self._run('describe --tags', check=True)[0]
return self._run("describe --tags", check=True)[0]
def terminate(self):
if self._proc is None:
@@ -345,18 +458,22 @@ class Git:
pass
def _get_repo_dirs(self):
return (os.path.normpath(_) for _ in
self._run('rev-parse --show-toplevel --absolute-git-dir', check=True))
return (
os.path.normpath(_)
for _ in self._run(
"rev-parse --show-toplevel --absolute-git-dir", check=True
)
)
def _run(self, cmdstr: str, paths: list = None, output=True, check=False):
cmdlist = self.gitcmd + shlex.split(cmdstr)
if paths:
cmdlist.append('--')
cmdlist.append("--")
cmdlist.extend(paths)
popen_args = dict(universal_newlines=True, encoding='utf8')
popen_args = dict(universal_newlines=True, encoding="utf8")
if not self.errors:
popen_args['stderr'] = subprocess.DEVNULL
log.trace("Executing: %s", ' '.join(cmdlist))
popen_args["stderr"] = subprocess.DEVNULL
log.trace("Executing: %s", " ".join(cmdlist))
if not output:
return subprocess.call(cmdlist, **popen_args)
if check:
@@ -379,30 +496,26 @@ def parse_log(filelist, dirlist, stats, git, merge=False, filterlist=None):
mtime = 0
datestr = isodate(0)
for line in git.log(
merge,
args.first_parent,
args.commit_time,
args.reverse_order,
filterlist
merge, args.first_parent, args.commit_time, args.reverse_order, filterlist
):
stats['loglines'] += 1
stats["loglines"] += 1
# Blank line between Date and list of files
if not line:
continue
# Date line
if line[0] != ':': # Faster than `not line.startswith(':')`
stats['commits'] += 1
if line[0] != ":": # Faster than `not line.startswith(':')`
stats["commits"] += 1
mtime = int(line)
if args.unique_times:
mtime = get_mtime_ns(mtime, stats['commits'])
mtime = get_mtime_ns(mtime, stats["commits"])
if args.debug:
datestr = isodate(mtime)
continue
# File line: three tokens if it describes a renaming, otherwise two
tokens = line.split('\t')
tokens = line.split("\t")
# Possible statuses:
# M: Modified (content changed)
@@ -411,7 +524,7 @@ def parse_log(filelist, dirlist, stats, git, merge=False, filterlist=None):
# T: Type changed: to/from regular file, symlinks, submodules
# R099: Renamed (moved), with % of unchanged content. 100 = pure rename
# Not possible in log: C=Copied, U=Unmerged, X=Unknown, B=pairing Broken
status = tokens[0].split(' ')[-1]
status = tokens[0].split(" ")[-1]
file = tokens[-1]
# Handles non-ASCII chars and OS path separator
@@ -419,56 +532,76 @@ def parse_log(filelist, dirlist, stats, git, merge=False, filterlist=None):
def do_file():
if args.skip_older_than_commit and get_mtime_path(file) <= mtime:
stats['skip'] += 1
stats["skip"] += 1
return
if args.debug:
log.debug("%d\t%d\t%d\t%s\t%s",
stats['loglines'], stats['commits'], stats['files'],
datestr, file)
log.debug(
"%d\t%d\t%d\t%s\t%s",
stats["loglines"],
stats["commits"],
stats["files"],
datestr,
file,
)
try:
touch(os.path.join(git.workdir, file), mtime)
stats['touches'] += 1
stats["touches"] += 1
except Exception as e:
log.error("ERROR: %s: %s", e, file)
stats['errors'] += 1
stats["errors"] += 1
def do_dir():
if args.debug:
log.debug("%d\t%d\t-\t%s\t%s",
stats['loglines'], stats['commits'],
datestr, "{}/".format(dirname or '.'))
log.debug(
"%d\t%d\t-\t%s\t%s",
stats["loglines"],
stats["commits"],
datestr,
"{}/".format(dirname or "."),
)
try:
touch(os.path.join(git.workdir, dirname), mtime)
stats['dirtouches'] += 1
stats["dirtouches"] += 1
except Exception as e:
log.error("ERROR: %s: %s", e, dirname)
stats['direrrors'] += 1
stats["direrrors"] += 1
if file in filelist:
stats['files'] -= 1
stats["files"] -= 1
filelist.remove(file)
do_file()
if args.dirs and status in ('A', 'D'):
if args.dirs and status in ("A", "D"):
dirname = os.path.dirname(file)
if dirname in dirlist:
dirlist.remove(dirname)
do_dir()
# All files done?
if not stats['files']:
if not stats["files"]:
git.terminate()
return
# Main Logic ##################################################################
def main():
start = time.time() # yes, Wall time. CPU time is not realistic for users.
stats = {_: 0 for _ in ('loglines', 'commits', 'touches', 'skip', 'errors',
'dirtouches', 'direrrors')}
stats = {
_: 0
for _ in (
"loglines",
"commits",
"touches",
"skip",
"errors",
"dirtouches",
"direrrors",
)
}
logging.basicConfig(level=args.loglevel, format='%(message)s')
logging.basicConfig(level=args.loglevel, format="%(message)s")
log.trace("Arguments: %s", args)
# First things first: Where and Who are we?
@@ -499,13 +632,16 @@ def main():
# Symlink (to file, to dir or broken - git handles the same way)
if not UPDATE_SYMLINKS and os.path.islink(fullpath):
log.warning("WARNING: Skipping symlink, no OS support for updates: %s",
path)
log.warning(
"WARNING: Skipping symlink, no OS support for updates: %s", path
)
continue
# skip files which are older than given threshold
if (args.skip_older_than
and start - get_mtime_path(fullpath) > args.skip_older_than):
if (
args.skip_older_than
and start - get_mtime_path(fullpath) > args.skip_older_than
):
continue
# Always add files relative to worktree root
@@ -519,15 +655,17 @@ def main():
else:
dirty = set(git.ls_dirty())
if dirty:
log.warning("WARNING: Modified files in the working directory were ignored."
"\nTo include such files, commit your changes or use --force.")
log.warning(
"WARNING: Modified files in the working directory were ignored."
"\nTo include such files, commit your changes or use --force."
)
filelist -= dirty
# Build dir list to be processed
dirlist = set(os.path.dirname(_) for _ in filelist) if args.dirs else set()
stats['totalfiles'] = stats['files'] = len(filelist)
log.info("{0:,} files to be processed in work dir".format(stats['totalfiles']))
stats["totalfiles"] = stats["files"] = len(filelist)
log.info("{0:,} files to be processed in work dir".format(stats["totalfiles"]))
if not filelist:
# Nothing to do. Exit silently and without errors, just like git does
@@ -544,10 +682,18 @@ def main():
if args.missing and not args.merge:
filterlist = list(filelist)
missing = len(filterlist)
log.info("{0:,} files not found in log, trying merge commits".format(missing))
log.info(
"{0:,} files not found in log, trying merge commits".format(missing)
)
for i in range(0, missing, STEPMISSING):
parse_log(filelist, dirlist, stats, git,
merge=True, filterlist=filterlist[i:i + STEPMISSING])
parse_log(
filelist,
dirlist,
stats,
git,
merge=True,
filterlist=filterlist[i : i + STEPMISSING],
)
# Still missing some?
for file in filelist:
@@ -556,29 +702,33 @@ def main():
# Final statistics
# Suggestion: use git-log --before=mtime to brag about skipped log entries
def log_info(msg, *a, width=13):
ifmt = '{:%d,}' % (width,) # not using 'n' for consistency with ffmt
ffmt = '{:%d,.2f}' % (width,)
ifmt = "{:%d,}" % (width,) # not using 'n' for consistency with ffmt
ffmt = "{:%d,.2f}" % (width,)
# %-formatting lacks a thousand separator, must pre-render with .format()
log.info(msg.replace('%d', ifmt).replace('%f', ffmt).format(*a))
log.info(msg.replace("%d", ifmt).replace("%f", ffmt).format(*a))
log_info(
"Statistics:\n"
"%f seconds\n"
"%d log lines processed\n"
"%d commits evaluated",
time.time() - start, stats['loglines'], stats['commits'])
"Statistics:\n%f seconds\n%d log lines processed\n%d commits evaluated",
time.time() - start,
stats["loglines"],
stats["commits"],
)
if args.dirs:
if stats['direrrors']: log_info("%d directory update errors", stats['direrrors'])
log_info("%d directories updated", stats['dirtouches'])
if stats["direrrors"]:
log_info("%d directory update errors", stats["direrrors"])
log_info("%d directories updated", stats["dirtouches"])
if stats['touches'] != stats['totalfiles']:
log_info("%d files", stats['totalfiles'])
if stats['skip']: log_info("%d files skipped", stats['skip'])
if stats['files']: log_info("%d files missing", stats['files'])
if stats['errors']: log_info("%d file update errors", stats['errors'])
if stats["touches"] != stats["totalfiles"]:
log_info("%d files", stats["totalfiles"])
if stats["skip"]:
log_info("%d files skipped", stats["skip"])
if stats["files"]:
log_info("%d files missing", stats["files"])
if stats["errors"]:
log_info("%d file update errors", stats["errors"])
log_info("%d files updated", stats['touches'])
log_info("%d files updated", stats["touches"])
if args.test:
log.info("TEST RUN - No files modified!")