Files
json/tools/serve_header/serve_header.py
Niels Lohmann ea9c4a2501 Document tools/macro_builder and tidy up serve_header.py
tools/macro_builder generates the NLOHMANN_JSON_EXPAND,
NLOHMANN_JSON_GET_MACRO and NLOHMANN_JSON_PASTE* macros in
macro_scope.hpp, but nothing referred to it. Add a README that explains
what it generates, how to run it and where the output goes, and which
dependent tables (NLOHMANN_JSON_DOUBLE_PASTE, NLOHMANN_JSON_TYPE_BODY)
are maintained by hand. Point to it from a comment above
NLOHMANN_JSON_EXPAND. The generator itself is unchanged; following the
README reproduces the header byte for byte.

In serve_header.py, drop the LGTM suppression (LGTM.com shut down in
2022), replace the """.""" placeholder docstrings with real ones, and
import socket and ssl at module level. DualStackServer.server_bind uses
socket, which was only imported under __main__; when the module was
imported instead, the NameError was swallowed and IPV6_V6ONLY was not
cleared.

The header change is a comment only; behavior, API and ABI are
unchanged.

Part of #5717

Signed-off-by: Niels Lohmann <mail@nlohmann.me>
2026-09-30 09:45:44 +02:00

433 lines
16 KiB
Python
Executable File

#!/usr/bin/env python3
import contextlib
import logging
import os
import re
import shutil
import socket
import ssl
import sys
import subprocess
from datetime import datetime, timedelta
from io import BytesIO
from threading import Lock, Timer
from watchdog.events import FileSystemEventHandler
from watchdog.observers import Observer
from http import HTTPStatus
from http.server import ThreadingHTTPServer, SimpleHTTPRequestHandler
CONFIG_FILE = 'serve_header.yml'
MAKEFILE = 'Makefile'
INCLUDE = 'include/nlohmann/'
SINGLE_INCLUDE = 'single_include/nlohmann/'
HEADER = 'json.hpp'
DATETIME_FORMAT = '%Y-%m-%d %H:%M:%S'
# origins whose pages may read the served header from a browser; Compiler
# Explorer downloads #include <https://...> headers client-side
DEFAULT_CORS_ORIGINS = ['https://godbolt.org', 'https://compiler-explorer.com']
JSON_VERSION_RE = re.compile(r'\s*#\s*define\s+NLOHMANN_JSON_VERSION_MAJOR\s+')
class ExitHandler(logging.StreamHandler):
def __init__(self, level):
"""Exit the process on log records at or above level."""
super().__init__()
self.level = level
def emit(self, record):
if record.levelno >= self.level:
sys.exit(1)
def is_project_root(test_dir='.'):
makefile = os.path.join(test_dir, MAKEFILE)
include = os.path.join(test_dir, INCLUDE)
single_include = os.path.join(test_dir, SINGLE_INCLUDE)
return (os.path.exists(makefile)
and os.path.isfile(makefile)
and os.path.exists(include)
and os.path.exists(single_include))
class DirectoryEventBucket:
def __init__(self, callback, delay=1.2, threshold=0.8):
"""Batch directory events and pass their common path to callback."""
self.delay = delay
self.threshold = timedelta(seconds=threshold)
self.callback = callback
self.event_dirs = set([])
self.timer = None
self.lock = Lock()
def start_timer(self):
if self.timer is None:
self.timer = Timer(self.delay, self.process_dirs)
self.timer.start()
def process_dirs(self):
result_dirs = []
event_dirs = set([])
with self.lock:
self.timer = None
while self.event_dirs:
time, event_dir = self.event_dirs.pop()
delta = datetime.now() - time
if delta < self.threshold:
event_dirs.add((time, event_dir))
else:
result_dirs.append(event_dir)
self.event_dirs = event_dirs
if result_dirs:
self.callback(os.path.commonpath(result_dirs))
if self.event_dirs:
self.start_timer()
def add_dir(self, path):
with self.lock:
# add path to the set of event_dirs if it is not a sibling of
# a directory already in the set
if not any(os.path.commonpath([path, event_dir]) == event_dir
for (_, event_dir) in self.event_dirs):
self.event_dirs.add((datetime.now(), path))
if self.timer is None:
self.start_timer()
class WorkTree:
make_command = 'make'
def __init__(self, root_dir, tree_dir):
"""Track the working tree at tree_dir and its amalgamated header."""
self.root_dir = root_dir
self.tree_dir = tree_dir
self.rel_dir = os.path.relpath(tree_dir, root_dir)
self.name = os.path.basename(tree_dir)
self.include_dir = os.path.abspath(os.path.join(tree_dir, INCLUDE))
self.header = os.path.abspath(os.path.join(tree_dir, SINGLE_INCLUDE, HEADER))
self.rel_header = os.path.relpath(self.header, root_dir)
self.dirty = True
self.build_count = 0
t = os.path.getmtime(self.header)
t = datetime.fromtimestamp(t)
self.build_time = t.strftime(DATETIME_FORMAT)
def __hash__(self):
"""Hash by working tree directory."""
return hash((self.tree_dir))
def __eq__(self, other):
"""Compare by working tree directory."""
if not isinstance(other, type(self)):
return NotImplemented
return self.tree_dir == other.tree_dir
def update_dirty(self, path):
if self.dirty:
return
path = os.path.abspath(path)
if os.path.commonpath([path, self.include_dir]) == self.include_dir:
logging.info(f'{self.name}: working tree marked dirty')
self.dirty = True
def amalgamate_header(self):
if not self.dirty:
return
mtime = os.path.getmtime(self.header)
subprocess.run([WorkTree.make_command, 'amalgamate'], cwd=self.tree_dir,
stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL)
if mtime == os.path.getmtime(self.header):
logging.info(f'{self.name}: no changes')
else:
self.build_count += 1
self.build_time = datetime.now().strftime(DATETIME_FORMAT)
logging.info(f'{self.name}: header amalgamated (build count {self.build_count})')
self.dirty = False
class WorkTrees(FileSystemEventHandler):
def __init__(self, root_dir):
"""Find the working trees below root_dir and watch it for changes."""
super().__init__()
self.root_dir = root_dir
self.trees = set([])
self.tree_lock = Lock()
self.scan(root_dir)
self.created_bucket = DirectoryEventBucket(self.scan)
self.observer = Observer()
self.observer.schedule(self, root_dir, recursive=True)
self.observer.start()
def scan(self, base_dir):
scan_dirs = set([base_dir])
# recursively scan base_dir for working trees
while scan_dirs:
scan_dir = os.path.abspath(scan_dirs.pop())
self.scan_tree(scan_dir)
try:
with os.scandir(scan_dir) as dir_it:
for entry in dir_it:
if entry.is_dir():
scan_dirs.add(entry.path)
except FileNotFoundError as e:
logging.debug('path disappeared: %s', e)
def scan_tree(self, scan_dir):
if not is_project_root(scan_dir):
return
# skip source trees in build directories
# this check could be enhanced
if scan_dir.endswith('/_deps/json-src'):
return
tree = WorkTree(self.root_dir, scan_dir)
with self.tree_lock:
if not tree in self.trees:
if tree.name == tree.rel_dir:
logging.info(f'adding working tree {tree.name}')
else:
logging.info(f'adding working tree {tree.name} at {tree.rel_dir}')
url = os.path.join('/', tree.rel_dir, HEADER)
logging.info(f'{tree.name}: serving header at {url}')
self.trees.add(tree)
def rescan(self, path=None):
if path is not None:
path = os.path.abspath(path)
trees = set([])
# check if any working trees have been removed
with self.tree_lock:
while self.trees:
tree = self.trees.pop()
if ((path is None
or os.path.commonpath([path, tree.tree_dir]) == tree.tree_dir)
and not is_project_root(tree.tree_dir)):
if tree.name == tree.rel_dir:
logging.info(f'removing working tree {tree.name}')
else:
logging.info(f'removing working tree {tree.name} at {tree.rel_dir}')
else:
trees.add(tree)
self.trees = trees
def find(self, path):
# find working tree for a given header file path
path = os.path.abspath(path)
with self.tree_lock:
for tree in self.trees:
if path == tree.header:
return tree
return None
def on_any_event(self, event):
logging.debug('%s (is_dir=%s): %s', event.event_type,
event.is_directory, event.src_path)
path = os.path.abspath(event.src_path)
if event.is_directory:
if event.event_type == 'created':
# check for new working trees
self.created_bucket.add_dir(path)
elif event.event_type == 'deleted':
# check for deleted working trees
self.rescan(path)
elif event.event_type == 'moved':
# handle moved directories - treat source as deleted and dest as created
self.rescan(path)
if hasattr(event, 'dest_path'):
dest_path = os.path.abspath(event.dest_path)
self.created_bucket.add_dir(dest_path)
elif event.event_type == 'closed':
with self.tree_lock:
for tree in self.trees:
tree.update_dirty(path)
def stop(self):
self.observer.stop()
self.observer.join()
class HeaderRequestHandler(SimpleHTTPRequestHandler):
cors_origins = DEFAULT_CORS_ORIGINS
def __init__(self, request, client_address, server):
"""Handle a request for a header below the working trees' root directory."""
self.worktrees = server.worktrees
self.worktree = None
try:
super().__init__(request, client_address, server,
directory=server.worktrees.root_dir)
except ConnectionResetError:
logging.debug('connection reset by peer')
def translate_path(self, path):
path = os.path.abspath(super().translate_path(path))
# add single_include/nlohmann into path, if needed
header = os.path.join('/', HEADER)
header_path = os.path.join('/', SINGLE_INCLUDE, HEADER)
if (path.endswith(header)
and not path.endswith(header_path)):
path = os.path.join(os.path.dirname(path), SINGLE_INCLUDE, HEADER)
return path
def send_head(self):
# check if the translated path matches a working tree
# and fulfill the request; otherwise, send 404
path = self.translate_path(self.path)
self.worktree = self.worktrees.find(path)
if self.worktree is not None:
self.worktree.amalgamate_header()
logging.info(f'{self.worktree.name}; serving header (build count {self.worktree.build_count})')
return super().send_head()
logging.info(f'invalid request path: {self.path}')
super().send_error(HTTPStatus.NOT_FOUND, 'Not Found')
return None
def send_header(self, keyword, value):
# intercept Content-Length header; sent in copyfile later
if keyword == 'Content-Length':
return
super().send_header(keyword, value)
def end_headers (self):
# intercept; called in copyfile() or indirectly
# by send_head via super().send_error()
pass
def copyfile(self, source, outputfile):
injected = False
content = BytesIO()
length = 0
# inject build count and time into served header
for line in source:
line = line.decode('utf-8')
if not injected and JSON_VERSION_RE.match(line):
length += content.write(bytes('#define JSON_BUILD_COUNT '\
f'{self.worktree.build_count}\n', 'utf-8'))
length += content.write(bytes('#define JSON_BUILD_TIME '\
f'"{self.worktree.build_time}"\n\n', 'utf-8'))
injected = True
length += content.write(bytes(line, 'utf-8'))
# set content length
super().send_header('Content-Length', length)
# CORS header; only for the configured origins
origin = self.headers.get('Origin')
if origin in self.cors_origins:
self.send_header('Access-Control-Allow-Origin', origin)
self.send_header('Vary', 'Origin')
# prevent caching
self.send_header('Cache-Control', 'no-cache, no-store, must-revalidate')
self.send_header('Pragma', 'no-cache')
self.send_header('Expires', '0')
super().end_headers()
# send the header
content.seek(0)
shutil.copyfileobj(content, outputfile)
def log_message(self, format, *args):
pass
class DualStackServer(ThreadingHTTPServer):
def __init__(self, addr, worktrees):
"""Serve the headers of worktrees on addr."""
self.worktrees = worktrees
super().__init__(addr, HeaderRequestHandler)
def server_bind(self):
# suppress exception when protocol is IPv4
with contextlib.suppress(Exception):
self.socket.setsockopt(
socket.IPPROTO_IPV6, socket.IPV6_V6ONLY, 0)
return super().server_bind()
if __name__ == '__main__':
import argparse
import yaml
# exit code
ec = 0
# setup logging
logging.basicConfig(format='[%(asctime)s] %(levelname)s: %(message)s',
datefmt=DATETIME_FORMAT, level=logging.INFO)
log = logging.getLogger()
log.addHandler(ExitHandler(logging.ERROR))
# parse command line arguments
parser = argparse.ArgumentParser()
parser.add_argument('--make', default='make',
help='the make command (default: make)')
args = parser.parse_args()
# propagate the make command to use for amalgamating headers
WorkTree.make_command = args.make
worktrees = None
try:
# change working directory to project root
os.chdir(os.path.realpath(os.path.join(sys.path[0], '../../')))
if not is_project_root():
log.error('working directory does not look like project root')
# load config
config = {}
config_file = os.path.abspath(CONFIG_FILE)
try:
with open(config_file, 'r') as f:
config = yaml.safe_load(f)
except FileNotFoundError:
log.info(f'cannot find configuration file: {config_file}')
log.info('using default configuration')
# find and monitor working trees
worktrees = WorkTrees(config.get('root', '.'))
# origins allowed to read the header from a browser
cors_origins = config.get('cors_origins', DEFAULT_CORS_ORIGINS)
if isinstance(cors_origins, str):
cors_origins = [cors_origins]
HeaderRequestHandler.cors_origins = cors_origins
# start web server; only reachable from this machine unless configured
# otherwise (bind: null listens on all interfaces)
infos = socket.getaddrinfo(config.get('bind', 'localhost'), config.get('port', 8443),
type=socket.SOCK_STREAM, flags=socket.AI_PASSIVE)
DualStackServer.address_family = infos[0][0]
HeaderRequestHandler.protocol_version = 'HTTP/1.0'
with DualStackServer(infos[0][4], worktrees) as httpd:
scheme = 'HTTP'
https = config.get('https', {})
if https.get('enabled', True):
cert_file = https.get('cert_file', 'localhost.pem')
key_file = https.get('key_file', 'localhost-key.pem')
ssl_ctx = ssl.create_default_context(ssl.Purpose.CLIENT_AUTH)
ssl_ctx.minimum_version = ssl.TLSVersion.TLSv1_2
ssl_ctx.maximum_version = ssl.TLSVersion.MAXIMUM_SUPPORTED
ssl_ctx.load_cert_chain(cert_file, key_file)
httpd.socket = ssl_ctx.wrap_socket(httpd.socket, server_side=True)
scheme = 'HTTPS'
host, port = httpd.socket.getsockname()[:2]
log.info(f'serving {scheme} on {host} port {port}')
log.info('press Ctrl+C to exit')
httpd.serve_forever()
except KeyboardInterrupt:
log.info('exiting')
except Exception:
ec = 1
log.exception('an error occurred:')
finally:
if worktrees is not None:
worktrees.stop()
sys.exit(ec)