Update standard headers

scripts/extract_std_headers.py

@@ -1,16 +1,20 @@
 #!/usr/bin/env python3
 
 """
-Given a file containing the text of https://en.cppreference.com/w/cpp/header create a list of std headers
+We are interested in the following headers:
+C++     - https://en.cppreference.com/w/cpp/header
+C       - https://en.cppreference.com/w/c/header
+POSIX C - https://en.wikipedia.org/wiki/C_POSIX_library
+
+Go to each site and copy the content into a file. This file then reads the file and prints a list we can use in the
+python file containing the standard header list for DWYU to lookup.
 """
 
 import re
 from pathlib import Path
 
-INPUT_FILE = Path("content_of_cppreference.txt")
-
-with INPUT_FILE.open(encoding="utf-8") as fin:
+with Path("input.txt").open(encoding="utf-8") as fin:
+    headers = []
     for line in fin.readlines():
-        include = re.findall("^<(.+)>$", line)
-        if len(include) == 1:
-            print(f'"{include[0]}",')  # noqa: T201
+        headers.extend(re.findall(r"<([a-z/.]+)>", line))
+    print("\n".join(f'"{h}",' for h in sorted(set(headers))))  # noqa: T201

src/analyze_includes/std_header.py

@@ -1,167 +1,201 @@
 """
-List is based on https://en.cppreference.com/w/cpp/header.
-The content of the website has been copied into a file (plain ctrl + c)
-and then extract_std_headers.py has been executed on the file.
+List is based on:
+C++     - https://en.cppreference.com/w/cpp/header
+C       - https://en.cppreference.com/w/c/header
+POSIX C - https://en.wikipedia.org/wiki/C_POSIX_library
 
-The list is a superset of all headers, no matter in which standard they have been introduced
-or if they are already removed. If you require a list tailored to a specific standard,
-you have to define it yourself and provide it to the tool through the CLI.
+The list is a superset of all headers, no matter in which standard they have been introduced or if they are already
+removed. If you require a list tailored to a specific standard, you have to define it yourself and provide it to DWYU
+via the 'ignored_includes' aspect option.
 """
 
-# extracted 2022.01.03
+# extracted 2024.05.03
 STD_HEADER = {
-    # concepts
-    "concepts",
-    # coroutines
-    "coroutine",
-    # utilities - generic
+    "aio.h",
+    "algorithm",
     "any",
+    "arpa/inet.h",
+    "array",
+    "assert.h",
+    "atomic",
+    "barrier",
+    "bit",
     "bitset",
+    "cassert",
+    "ccomplex",
+    "cctype",
+    "cerrno",
+    "cfenv",
+    "cfloat",
+    "charconv",
     "chrono",
+    "cinttypes",
+    "climits",
+    "clocale",
+    "cmath",
+    "codecvt",
     "compare",
+    "complex",
+    "complex.h",
+    "concepts",
+    "coroutine",
+    "cpio.h",
     "csetjmp",
     "csignal",
+    "cstdalign",
     "cstdarg",
+    "cstdatomic",
+    "cstdbool",
     "cstddef",
-    "cstdlib",
-    "ctime",
-    "functional",
-    "initializer_list",
-    "optional",
-    "source_location",
-    "stacktrace",
-    "tuple",
-    "type_traits",
-    "typeindex",
-    "typeinfo",
-    "utility",
-    "variant",
-    "version",
-    # utilities - dynamic memory management
-    "memory",
-    "memory_resource",
-    "new",
-    "scoped_allocator",
-    # utilities - numeric limits
-    "cfloat",
-    "cinttypes",
-    "climits",
     "cstdint",
-    "limits",
-    # utilities - error handling
-    "cassert",
-    "cerrno",
-    "exception",
-    "stdexcept",
-    "system_error",
-    # strings
-    "cctype",
-    "charconv",
+    "cstdio",
+    "cstdlib",
     "cstring",
+    "ctgmath",
+    "ctime",
+    "ctype.h",
     "cuchar",
     "cwchar",
     "cwctype",
-    "format",
-    "string",
-    "string_view",
-    # containers
-    "array",
+    "debugging",
     "deque",
-    "forward_list",
-    "list",
-    "map",
-    "queue",
-    "set",
-    "span",
-    "stack",
-    "unordered_map",
-    "unordered_set",
-    "vector",
-    # iterators
-    "iterator",
-    # ranges
-    "ranges",
-    # algorithms
-    "algorithm",
+    "dirent.h",
+    "dlfcn.h",
+    "errno.h",
+    "exception",
     "execution",
-    # numerics
-    "bit",
-    "cfenv",
-    "cmath",
-    "complex",
-    "numbers",
-    "numeric",
-    "random",
-    "ratio",
-    "valarray",
-    # localization
-    "clocale",
-    "codecvt",
-    "locale",
-    # input/output
-    "cstdio",
+    "expected",
+    "fcntl.h",
+    "fenv.h",
+    "filesystem",
+    "float.h",
+    "fmtmsg.h",
+    "fnmatch.h",
+    "format",
     "fstream",
+    "ftw.h",
+    "functional",
+    "future",
+    "generator",
+    "glob.h",
+    "grp.h",
+    "iconv.h",
+    "inttypes.h",
     "iomanip",
     "ios",
     "iosfwd",
     "iostream",
     "istream",
-    "ostream",
-    "spanstream",
-    "sstream",
-    "streambuf",
-    "strstream",
-    "syncstream",
-    # filesystem
-    "filesystem",
-    # regular expression
-    "regex",
-    # atomic operations
-    "atomic",
-    # thread support
-    "barrier",
-    "condition_variable",
-    "future",
+    "iterator",
+    "langinfo.h",
     "latch",
-    "mutex",
-    "semaphore",
-    "shared_mutex",
-    "stop_token",
-    "thread",
-    # C compatibility headers
-    "assert.h",
-    "ctype.h",
-    "errno.h",
-    "fenv.h",
-    "float.h",
-    "inttypes.h",
+    "libgen.h",
+    "limits",
     "limits.h",
+    "linalg",
+    "list",
+    "locale",
     "locale.h",
+    "map",
     "math.h",
+    "mdspan",
+    "memory",
+    "monetary.h",
+    "mqueue.h",
+    "mutex",
+    "ndbm.h",
+    "net/if.h",
+    "netdb.h",
+    "netinet/in.h",
+    "netinet/tcp.h",
+    "new",
+    "numbers",
+    "numeric",
+    "optional",
+    "ostream",
+    "poll.h",
+    "print",
+    "pthread.h",
+    "pwd.h",
+    "queue",
+    "random",
+    "ranges",
+    "ratio",
+    "rcu",
+    "regex",
+    "regex.h",
+    "sched.h",
+    "search.h",
+    "semaphore",
+    "semaphore.h",
+    "set",
     "setjmp.h",
     "signal.h",
+    "span",
+    "spanstream",
+    "spawn.h",
+    "sstream",
+    "stack",
+    "stacktrace",
+    "stdalign.h",
     "stdarg.h",
+    "stdatomic.h",
+    "stdbit.h",
+    "stdbool.h",
+    "stdckdint.h",
     "stddef.h",
+    "stdexcept",
+    "stdfloat",
     "stdint.h",
     "stdio.h",
     "stdlib.h",
+    "stdnoreturn.h",
+    "streambuf",
+    "string",
     "string.h",
+    "strings.h",
+    "stropts.h",
+    "strstream",
+    "syncstream",
+    "sys/ipc.h",
+    "sys/mman.h",
+    "sys/msg.h",
+    "sys/resource.h",
+    "sys/select.h",
+    "sys/sem.h",
+    "sys/shm.h",
+    "sys/socket.h",
+    "sys/stat.h",
+    "sys/statvfs.h",
+    "sys/time.h",
+    "sys/times.h",
+    "sys/types.h",
+    "sys/uio.h",
+    "sys/un.h",
+    "sys/utsname.h",
+    "sys/wait.h",
+    "syslog.h",
+    "tar.h",
+    "termios.h",
+    "tgmath.h",
+    "thread",
+    "threads.h",
     "time.h",
+    "trace.h",
+    "tuple",
+    "typeindex",
+    "typeinfo",
     "uchar.h",
+    "ulimit.h",
+    "unistd.h",
+    "utility",
+    "utime.h",
+    "utmpx.h",
+    "valarray",
+    "variant",
+    "vector",
+    "version",
     "wchar.h",
     "wctype.h",
-    # special C compatibility headers
-    "stdatomic.h",
-    # Empty C headers
-    "ccomplex",
-    "complex.h",
-    "ctgmath",
-    "tgmath.h",
-    # Meaningless C headers
-    "ciso646",
-    "cstdalign",
-    "cstdbool",
-    "iso646.h",
-    "stdalign.h",
-    "stdbool.h",
+    "wordexp.h",
 }