/*
 * Copyright (C) 2012-2021 Robin Haberkorn
 *
 * This program is free software: you can redistribute it and/or modify
 * it under the terms of the GNU General Public License as published by
 * the Free Software Foundation, either version 3 of the License, or
 * (at your option) any later version.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program.  If not, see <http://www.gnu.org/licenses/>.
 */

#ifdef HAVE_CONFIG_H
#include "config.h"
#endif

#include <string.h>

#include <glib.h>
#include <glib/gprintf.h>
#include <glib/gstdio.h>

#include "sciteco.h"
#include "string-utils.h"
#include "file-utils.h"
#include "interface.h"
#include "parser.h"
#include "core-commands.h"
#include "expressions.h"
#include "qreg.h"
#include "ring.h"
#include "error.h"
#include "glob.h"

/*
 * FIXME: This state could be static.
 */
TECO_DECLARE_STATE(teco_state_glob_filename);

/** @memberof teco_globber_t */
void
teco_globber_init(teco_globber_t *ctx, const gchar *pattern, GFileTest test)
{
	memset(ctx, 0, sizeof(*ctx));
	ctx->test = test;

	/*
	 * This finds the directory component including
	 * any trailing directory separator
	 * without making up a directory if it is missing
	 * (as g_path_get_dirname() does).
	 * Important since it allows us to construct
	 * file names with the exact same directory
	 * prefix as the input pattern.
	 */
	gsize dirname_len = teco_file_get_dirname_len(pattern);
	ctx->dirname = g_strndup(pattern, dirname_len);

	ctx->dir = g_dir_open(*ctx->dirname ? ctx->dirname : ".", 0, NULL);
	/* if dirname does not exist, the result may be NULL */

	ctx->pattern = teco_globber_compile_pattern(pattern + dirname_len);
}

/** @memberof teco_globber_t */
gchar *
teco_globber_next(teco_globber_t *ctx)
{
	const gchar *basename;

	if (!ctx->dir)
		return NULL;

	while ((basename = g_dir_read_name(ctx->dir))) {
		if (!g_regex_match(ctx->pattern, basename, 0, NULL))
			continue;

		/*
		 * As dirname includes the directory separator,
		 * we can simply concatenate dirname with basename.
		 */
		gchar *filename = g_strconcat(ctx->dirname, basename, NULL);

		/*
		 * No need to perform file test for EXISTS since
		 * g_dir_read_name() will only return existing entries
		 */
		if (ctx->test == G_FILE_TEST_EXISTS || g_file_test(filename, ctx->test))
			return filename;

		g_free(filename);
	}

	return NULL;
}

/** @memberof teco_globber_t */
void
teco_globber_clear(teco_globber_t *ctx)
{
	if (ctx->pattern)
		g_regex_unref(ctx->pattern);
	if (ctx->dir)
		g_dir_close(ctx->dir);
	g_free(ctx->dirname);
}

/** @static @memberof teco_globber_t */
gchar *
teco_globber_escape_pattern(const gchar *pattern)
{
	gsize escaped_len = 1;
	gchar *escaped, *pout;

	/*
	 * NOTE: The exact size of the escaped string is easy to calculate
	 * in O(n) just like strlen(pattern), so we can just as well
	 * do that.
	 */
	for (const gchar *pin = pattern; *pin; pin++) {
		switch (*pin) {
		case '*':
		case '?':
		case '[':
			escaped_len += 3;
			break;
		default:
			escaped_len++;
			break;
		}
	}
	pout = escaped = g_malloc(escaped_len);

	while (*pattern) {
		switch (*pattern) {
		case '*':
		case '?':
		case '[':
			*pout++ = '[';
			*pout++ = *pattern;
			*pout++ = ']';
			break;
		default:
			*pout++ = *pattern;
			break;
		}

		pattern++;
	}
	*pout = '\0';

	return escaped;
}

/**
 * Compile a fnmatch(3)-compatible glob pattern to
 * a PCRE regular expression.
 *
 * There is GPattern, but it only supports the
 * "*" and "?" wildcards which most importantly
 * do not allow escaping.
 *
 * @param pattern The pattern to compile.
 * @return A new compiled regular expression object.
 *         Always non-NULL. Unref after use.
 *
 * @static @memberof teco_globber_t
 */
GRegex *
teco_globber_compile_pattern(const gchar *pattern)
{
	enum {
		STATE_WILDCARD,
		STATE_CLASS_START,
		STATE_CLASS_NEGATE,
		STATE_CLASS
	} state = STATE_WILDCARD;

	/*
	 * NOTE: The conversion to regex needs at most two
	 * characters per input character and the regex pattern
	 * is required only temporarily, so we use a fixed size
	 * buffer avoiding reallocations but wasting a few bytes
	 * (determining the exact required space would be tricky).
	 * It is not allocated on the stack though since pattern
	 * might be arbitrary user input and we must avoid
	 * stack overflows at all costs.
	 */
	g_autofree gchar *pattern_regex = g_malloc(strlen(pattern)*2 + 1 + 1);
	gchar *pout = pattern_regex;

	while (*pattern) {
		if (state == STATE_WILDCARD) {
			/*
			 * Outside a character class/set.
			 */
			switch (*pattern) {
			case '*':
				*pout++ = '.';
				*pout++ = '*';
				break;
			case '?':
				*pout++ = '.';
				break;
			case '[':
				/*
				 * The special case of an unclosed character
				 * class is allowed in fnmatch(3) but invalid
				 * in PCRE, so we must check for it explicitly.
				 * FIXME: This is sort of inefficient...
				 */
				if (strchr(pattern, ']')) {
					state = STATE_CLASS_START;
					*pout++ = '[';
					break;
				}
				/* fall through */
			default:
				/*
				 * For simplicity, all non-alphanumeric
				 * characters are escaped since they could
				 * be PCRE magic characters.
				 * g_regex_escape_string() is inefficient.
				 * character anyway.
				 */
				if (!g_ascii_isalnum(*pattern))
					*pout++ = '\\';
				*pout++ = *pattern;
				break;
			}
		} else {
			/*
			 * Within a character class/set.
			 */
			switch (*pattern) {
			case '!':
				/*
				 * fnmatch(3) allows ! instead of ^ immediately
				 * after the opening bracket.
				 */
				if (state > STATE_CLASS_START) {
					state = STATE_CLASS;
					*pout++ = '!';
					break;
				}
				/* fall through */
			case '^':
				state = state == STATE_CLASS_START
					? STATE_CLASS_NEGATE : STATE_CLASS;
				*pout++ = '^';
				break;
			case ']':
				/*
				 * fnmatch(3) allows the closing bracket as the
				 * first character to include it in the set, while
				 * PCRE requires it to be escaped.
				 */
				if (state == STATE_CLASS) {
					state = STATE_WILDCARD;
					*pout++ = ']';
					break;
				}
				/* fall through */
			default:
				if (!g_ascii_isalnum(*pattern))
					*pout++ = '\\';
				/* fall through */
			case '-':
				state = STATE_CLASS;
				*pout++ = *pattern;
				break;
			}
		}

		pattern++;
	}
	*pout++ = '$';
	*pout = '\0';

	GRegex *pattern_compiled = g_regex_new(pattern_regex,
	                                       G_REGEX_DOTALL | G_REGEX_ANCHORED, 0, NULL);
	/*
	 * Since the regex is generated from patterns that are
	 * always valid, there must be no syntactic error.
	 */
	g_assert(pattern_compiled != NULL);

	return pattern_compiled;
}

/*
 * Command States
 */

static teco_state_t *
teco_state_glob_pattern_done(teco_machine_main_t *ctx, const teco_string_t *str, GError **error)
{
	if (ctx->mode > TECO_MODE_NORMAL)
		return &teco_state_glob_filename;

	if (str->len > 0) {
		g_autofree gchar *filename = teco_file_expand_path(str->data);

		teco_qreg_t *glob_reg = teco_qreg_table_find(&teco_qreg_table_globals, "_", 1);
		g_assert(glob_reg != NULL);
		if (!glob_reg->vtable->undo_set_string(glob_reg, error) ||
		    !glob_reg->vtable->set_string(glob_reg, filename, strlen(filename), error))
			return NULL;
	}

	return &teco_state_glob_filename;
}

/*$ EN glob
 * [type]EN[pattern]$[filename]$ -- Glob files or match filename and check file type
 * [type]:EN[pattern]$[filename]$ -> Success|Failure
 *
 * EN is a powerful command for performing various tasks
 * given a glob \fIpattern\fP.
 * For a description of the glob pattern syntax, refer to the section
 * .B Glob Patterns
 * for details.
 *
 * \fIpattern\fP may be omitted, in which case it defaults
 * to the pattern saved in the search and glob register \(lq_\(rq.
 * If it is specified, it overwrites the contents of the register
 * \(lq_\(rq with \fIpattern\fP.
 * This behaviour is similar to the search and replace commands
 * and allows for repeated gloHTTP/1.1 200 OK
Connection: keep-alive
Connection: keep-alive
Content-Disposition: inline; filename="glob.c"
Content-Disposition: inline; filename="glob.c"
Content-Length: 16786
Content-Length: 16786
Content-Security-Policy: default-src 'none'
Content-Security-Policy: default-src 'none'
Content-Type: text/plain; charset=UTF-8
Content-Type: text/plain; charset=UTF-8
Date: Wed, 22 Oct 2025 01:40:38 UTC
ETag: "f6810c2731f8ff54cc11b8378c5cd6f010c7051b"
ETag: "f6810c2731f8ff54cc11b8378c5cd6f010c7051b"
Expires: Sat, 20 Oct 2035 01:40:38 GMT
Expires: Sat, 20 Oct 2035 01:40:38 GMT
Last-Modified: Wed, 22 Oct 2025 01:40:38 GMT
Last-Modified: Wed, 22 Oct 2025 01:40:38 GMT
Server: OpenBSD httpd
Server: OpenBSD httpd
X-Content-Type-Options: nosniff
X-Content-Type-Options: nosniff

/*
 * Copyright (C) 2012-2021 Robin Haberkorn
 *
 * This program is free software: you can redistribute it and/or modify
 * it under the terms of the GNU General Public License as published by
 * the Free Software Foundation, either version 3 of the License, or
 * (at your option) any later version.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program.  If not, see <http://www.gnu.org/licenses/>.
 */

#ifdef HAVE_CONFIG_H
#include "config.h"
#endif

#include <string.h>

#include <glib.h>
#include <glib/gprintf.h>
#include <glib/gstdio.h>

#include "sciteco.h"
#include "string-utils.h"
#include "file-utils.h"
#include "interface.h"
#include "parser.h"
#include "core-commands.h"
#include "expressions.h"
#include "qreg.h"
#include "ring.h"
#include "error.h"
#include "glob.h"

/*
 * FIXME: This state could be static.
 */
TECO_DECLARE_STATE(teco_state_glob_filename);

/** @memberof teco_globber_t */
void
teco_globber_init(teco_globber_t *ctx, const gchar *pattern, GFileTest test)
{
	memset(ctx, 0, sizeof(*ctx));
	ctx->test = test;

	/*
	 * This finds the directory component including
	 * any trailing directory separator
	 * without making up a directory if it is missing
	 * (as g_path_get_dirname() does).
	 * Important since it allows us to construct
	 * file names with the exact same directory
	 * prefix as the input pattern.
	 */
	gsize dirname_len = teco_file_get_dirname_len(pattern);
	ctx->dirname = g_strndup(pattern, dirname_len);

	ctx->dir = g_dir_open(*ctx->dirname ? ctx->dirname : ".", 0, NULL);
	/* if dirname does not exist, the result may be NULL */

	ctx->pattern = teco_globber_compile_pattern(pattern + dirname_len);
}

/** @memberof teco_globber_t */
gchar *
teco_globber_next(teco_globber_t *ctx)
{
	const gchar *basename;

	if (!ctx->dir)
		return NULL;

	while ((basename = g_dir_read_name(ctx->dir))) {
		if (!g_regex_match(ctx->pattern, basename, 0, NULL))
			continue;

		/*
		 * As dirname includes the directory separator,
		 * we can simply concatenate dirname with basename.
		 */
		gchar *filename = g_strconcat(ctx->dirname, basename, NULL);

		/*
		 * No need to perform file test for EXISTS since
		 * g_dir_read_name() will only return existing entries
		 */
		if (ctx->test == G_FILE_TEST_EXISTS || g_file_test(filename, ctx->test))
			return filename;

		g_free(filename);
	}

	return NULL;
}

/** @memberof teco_globber_t */
void
teco_globber_clear(teco_globber_t *ctx)
{
	if (ctx->pattern)
		g_regex_unref(ctx->pattern);
	if (ctx->dir)
		g_dir_close(ctx->dir);
	g_free(ctx->dirname);
}

/** @static @memberof teco_globber_t */
gchar *
teco_globber_escape_pattern(const gchar *pattern)
{
	gsize escaped_len = 1;
	gchar *escaped, *pout;

	/*
	 * NOTE: The exact size of the escaped string is easy to calculate
	 * in O(n) just like strlen(pattern), so we can just as well
	 * do that.
	 */
	for (const gchar *pin = pattern; *pin; pin++) {
		switch (*pin) {
		case '*':
		case '?':
		case '[':
			escaped_len += 3;
			break;
		default:
			escaped_len++;
			break;
		}
	}
	pout = escaped = g_malloc(escaped_len);

	while (*pattern) {
		switch (*pattern) {
		case '*':
		case '?':
		case '[':
			*pout++ = '[';
			*pout++ = *pattern;
			*pout++ = ']';
			break;
		default:
			*pout++ = *pattern;
			break;
		}

		pattern++;
	}
	*pout = '\0';

	return escaped;
}

/**
 * Compile a fnmatch(3)-compatible glob pattern to
 * a PCRE regular expression.
 *
 * There is GPattern, but it only supports the
 * "*" and "?" wildcards which most importantly
 * do not allow escaping.
 *
 * @param pattern The pattern to compile.
 * @return A new compiled regular expression object.
 *         Always non-NULL. Unref after use.
 *
 * @static @memberof teco_globber_t
 */
GRegex *
teco_globber_compile_pattern(const gchar *pattern)
{
	enum {
		STATE_WILDCARD,
		STATE_CLASS_START,
		STATE_CLASS_NEGATE,
		STATE_CLASS
	} state = STATE_WILDCARD;

	/*
	 * NOTE: The conversion to regex needs at most two
	 * characters per input character and the regex pattern
	 * is required only temporarily, so we use a fixed size
	 * buffer avoiding reallocations but wasting a few bytes
	 * (determining the exact required space would be tricky).
	 * It is not allocated on the stack though since pattern
	 * might be arbitrary user input and we must avoid
	 * stack overflows at all costs.
	 */
	g_autofree gchar *pattern_regex = g_malloc(strlen(pattern)*2 + 1 + 1);
	gchar *pout = pattern_regex;

	while (*pattern) {
		if (state == STATE_WILDCARD) {
			/*
			 * Outside a character class/set.
			 */
			switch (*pattern) {
			case '*':
				*pout++ = '.';
				*pout++ = '*';
				break;
			case '?':
				*pout++ = '.';
				break;
			case '[':
				/*
				 * The special case of an unclosed character
				 * class is allowed in fnmatch(3) but invalid
				 * in PCRE, so we must check for it explicitly.
				 * FIXME: This is sort of inefficient...
				 */
				if (strchr(pattern, ']')) {
					state = STATE_CLASS_START;
					*pout++ = '[';
					break;
				}
				/* fall through */
			default:
				/*
				 * For simplicity, all non-alphanumeric
				 * characters are escaped since they could
				 * be PCRE magic characters.
				 * g_regex_escape_string() is inefficient.
				 * character anyway.
				 */
				if (!g_ascii_isalnum(*pattern))
					*pout++ = '\\';
				*pout++ = *pattern;
				break;
			}
		} else {
			/*
			 * Within a character class/set.
			 */
			switch (*pattern) {
			case '!':
				/*
				 * fnmatch(3) allows ! instead of ^ immediately
				 * after the opening bracket.
				 */
				if (state > STATE_CLASS_START) {
					state = STATE_CLASS;
					*pout++ = '!';
					break;
				}
				/* fall through */
			case '^':
				state = state == STATE_CLASS_START
					? STATE_CLASS_NEGATE : STATE_CLASS;
				*pout++ = '^';
				break;
			case ']':
				/*
				 * fnmatch(3) allows the closing bracket as the
				 * first character to include it in the set, while
				 * PCRE requires it to be escaped.
				 */
				if (state == STATE_CLASS) {
					state = STATE_WILDCARD;
					*pout++ = ']';
					break;
				}
				/* fall through */
			default:
				if (!g_ascii_isalnum(*pattern))
					*pout++ = '\\';
				/* fall through */
			case '-':
				state = STATE_CLASS;
				*pout++ = *pattern;
				break;
			}
		}

		pattern++;
	}
	*pout++ = '$';
	*pout = '\0';

	GRegex *pattern_compiled = g_regex_new(pattern_regex,
	                                       G_REGEX_DOTALL | G_REGEX_ANCHORED, 0, NULL);
	/*
	 * Since the regex is generated from patterns that are
	 * always valid, there must be no syntactic error.
	 */
	g_assert(pattern_compiled != NULL);

	return pattern_compiled;
}

/*
 * Command States
 */

static teco_state_t *
teco_state_glob_pattern_done(teco_machine_main_t *ctx, const teco_string_t *str, GError **error)
{
	if (ctx->mode > TECO_MODE_NORMAL)
		return &teco_state_glob_filename;

	if (str->len > 0) {
		g_autofree gchar *filename = teco_file_expand_path(str->data);

		teco_qreg_t *glob_reg = teco_qreg_table_find(&teco_qreg_table_globals, "_", 1);
		g_assert(glob_reg != NULL);
		if (!glob_reg->vtable->undo_set_string(glob_reg, error) ||
		    !glob_reg->vtable->set_string(glob_reg, filename, strlen(filename), error))
			return NULL;
	}

	return &teco_state_glob_filename;
}

/*$ EN glob
 * [type]EN[pattern]$[filename]$ -- Glob files or match filename and check file type
 * [type]:EN[pattern]$[filename]$ -> Success|Failure
 *
 * EN is a powerful command for performing various tasks
 * given a glob \fIpattern\fP.
 * For a description of the