path: root/scripts/list-gitignored.c

// SPDX-License-Identifier: GPL-2.0-only
//
// Traverse the source tree, parsing all .gitignore files, and print file paths
// that are ignored by git.
// The output is suitable to the --exclude-from option of tar.
// This is useful until the --exclude-vcs-ignores option gets working correctly.
//
// Copyright (C) 2023 Masahiro Yamada <masahiroy@kernel.org>
//                      (a lot of code imported from GIT)

#include <assert.h>
#include <dirent.h>
#include <errno.h>
#include <fcntl.h>
#include <getopt.h>
#include <stdarg.h>
#include <stdbool.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <sys/stat.h>
#include <sys/types.h>
#include <unistd.h>

// Imported from commit 23c56f7bd5f1667f8b793d796bf30e39545920f6 in GIT
//
//---------------------------(IMPORT FROM GIT BEGIN)---------------------------

// Copied from environment.c

static bool ignore_case;

// Copied from git-compat-util.h

/* Sane ctype - no locale, and works with signed chars */
#undef isascii
#undef isspace
#undef isdigit
#undef isalpha
#undef isalnum
#undef isprint
#undef islower
#undef isupper
#undef tolower
#undef toupper
#undef iscntrl
#undef ispunct
#undef isxdigit

static const unsigned char sane_ctype[256];
#define GIT_SPACE 0x01
#define GIT_DIGIT 0x02
#define GIT_ALPHA 0x04
#define GIT_GLOB_SPECIAL 0x08
#define GIT_REGEX_SPECIAL 0x10
#define GIT_PATHSPEC_MAGIC 0x20
#define GIT_CNTRL 0x40
#define GIT_PUNCT 0x80
#define sane_istest(x,mask) ((sane_ctype[(unsigned char)(x)] & (mask)) != 0)
#define isascii(x) (((x) & ~0x7f) == 0)
#define isspace(x) sane_istest(x,GIT_SPACE)
#define isdigit(x) sane_istest(x,GIT_DIGIT)
#define isalpha(x) sane_istest(x,GIT_ALPHA)
#define isalnum(x) sane_istest(x,GIT_ALPHA | GIT_DIGIT)
#define isprint(x) ((x) >= 0x20 && (x) <= 0x7e)
#define islower(x) sane_iscase(x, 1)
#define isupper(x) sane_iscase(x, 0)
#define is_glob_special(x) sane_istest(x,GIT_GLOB_SPECIAL)
#define iscntrl(x) (sane_istest(x,GIT_CNTRL))
#define ispunct(x) sane_istest(x, GIT_PUNCT | GIT_REGEX_SPECIAL | \
		GIT_GLOB_SPECIAL | GIT_PATHSPEC_MAGIC)
#define isxdigit(x) (hexval_table[(unsigned char)(x)] != -1)
#define tolower(x) sane_case((unsigned char)(x), 0x20)
#define toupper(x) sane_case((unsigned char)(x), 0)

static inline int sane_case(int x, int high)
{
	if (sane_istest(x, GIT_ALPHA))
		x = (x & ~0x20) | high;
	return x;
}

static inline int sane_iscase(int x, int is_lower)
{
	if (!sane_istest(x, GIT_ALPHA))
		return 0;

	if (is_lower)
		return (x & 0x20) != 0;
	else
		return (x & 0x20) == 0;
}

// Copied from ctype.c

enum {
	S = GIT_SPACE,
	A = GIT_ALPHA,
	D = GIT_DIGIT,
	G = GIT_GLOB_SPECIAL,	/* *, ?, [, \\ */
	R = GIT_REGEX_SPECIAL,	/* $, (, ), +, ., ^, {, | */
	P = GIT_PATHSPEC_MAGIC, /* other non-alnum, except for ] and } */
	X = GIT_CNTRL,
	U = GIT_PUNCT,
	Z = GIT_CNTRL | GIT_SPACE
};

static const unsigned char sane_ctype[256] = {
	X, X, X, X, X, X, X, X, X, Z, Z, X, X, Z, X, X,		/*   0.. 15 */
	X, X, X, X, X, X, X, X, X, X, X, X, X, X, X, X,		/*  16.. 31 */
	S, P, P, P, R, P, P, P, R, R, G, R, P, P, R, P,		/*  32.. 47 */
	D, D, D, D, D, D, D, D, D, D, P, P, P, P, P, G,		/*  48.. 63 */
	P, A, A, A, A, A, A, A, A, A, A, A, A, A, A, A,		/*  64.. 79 */
	A, A, A, A, A, A, A, A, A, A, A, G, G, U, R, P,		/*  80.. 95 */
	P, A, A, A, A, A, A, A, A, A, A, A, A, A, A, A,		/*  96..111 */
	A, A, A, A, A, A, A, A, A, A, A, R, R, U, P, X,		/* 112..127 */
	/* Nothing in the 128.. range */
};

// Copied from hex.c

static const signed char hexval_table[256] = {
	 -1, -1, -1, -1, -1, -1, -1, -1,		/* 00-07 */
	 -1, -1, -1, -1, -1, -1, -1, -1,		/* 08-0f */
	 -1, -1, -1, -1, -1, -1, -1, -1,		/* 10-17 */
	 -1, -1, -1, -1, -1, -1, -1, -1,		/* 18-1f */
	 -1, -1, -1, -1, -1, -1, -1, -1,		/* 20-27 */
	 -1, -1, -1, -1, -1, -1, -1, -1,		/* 28-2f */
	  0,  1,  2,  3,  4,  5,  6,  7,		/* 30-37 */
	  8,  9, -1, -1, -1, -1, -1, -1,		/* 38-3f */
	 -1, 10, 11, 12, 13, 14