Start writing a genunicode program to process the unicode data files. While we are here, add some missing copyright/license notices.

FossilOrigin-Name: 72aa02406da41a413284af19d52bcc1a091cac210b64f9887b123a95f20128e0

5 files changed, 98 insertions, 3 deletions

diff --git a/src/lib/Makefile.am b/src/lib/Makefile.am
index c95fe1c..9cbbfae 100644
--- a/src/lib/Makefile.am
+++ b/src/lib/Makefile.am
@@ -8,6 +8,7 @@ libaplwc_a_SOURCES = \
 	src/lib/module.c \
 	src/lib/string.c \
 	src/lib/symtab.c \
-	src/lib/syntax.c
+	src/lib/syntax.c \
+	src/lib/unicode.c
 
 EXTRA_DIST += src/lib/boot.aplwc
diff --git a/src/lib/unicode.c b/src/lib/unicode.c
index 862dd5f..a913b6d 100644
--- a/src/lib/unicode.c
+++ b/src/lib/unicode.c
@@ -18,3 +18,4 @@
  */
 
 #include "aplwc_internal.h"
+#include "unicode.h"
diff --git a/src/tools/Makefile.am b/src/tools/Makefile.am
index b1079e7..1930970 100644
--- a/src/tools/Makefile.am
+++ b/src/tools/Makefile.am
@@ -1,10 +1,16 @@
-noinst_PROGRAMS += genboot
+noinst_PROGRAMS += genboot genunicode
 
 genboot_SOURCES = src/tools/genboot.c
+genunicode_SOURCES = src/tools/genunicode.c
 
 BUILT_SOURCES += $(top_builddir)/generated/boot.h
-CLEANFILES += $(top_builddir)/generated/boot.h
+BUILT_SOURCES += $(top_builddir)/generated/unicode.h
 
 $(top_builddir)/generated/boot.h: genboot src/lib/boot.aplwc
 	$(MKDIR_P) $(top_builddir)/generated
 	./genboot $(top_srcdir)/src/lib/boot.aplwc > $@
+
+$(top_builddir)/generated/unicode.h: genunicode src/unicode/DerivedCoreProperties.txt src/unicode/PropList.txt
+	$(MKDIR_P) $(top_builddir)/generated
+	./genunicode $(top_srcdir)/src/unicode > $@
+
diff --git a/src/tools/genboot.c b/src/tools/genboot.c
index e89b3aa..9d0a7e4 100644
--- a/src/tools/genboot.c
+++ b/src/tools/genboot.c
@@ -1,3 +1,22 @@
+/* 
+ * Copyright (C) 2026 Peter Mikkelsen <petermikkelsen10@gmail.com>
+ *
+ * This file is part of aplwc.
+ *
+ * Aplwc 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.
+ *
+ * Aplwc 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 aplwc.  If not, see <https://www.gnu.org/licenses/>.
+ */
+
 #include <stdio.h>
 #include <assert.h>
 
diff --git a/src/tools/genunicode.c b/src/tools/genunicode.c
new file mode 100644
index 0000000..0329ace
--- /dev/null
+++ b/src/tools/genunicode.c
@@ -0,0 +1,68 @@
+/* 
+ * Copyright (C) 2026 Peter Mikkelsen <petermikkelsen10@gmail.com>
+ *
+ * This file is part of aplwc.
+ *
+ * Aplwc 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.
+ *
+ * Aplwc 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 aplwc.  If not, see <https://www.gnu.org/licenses/>.
+ */
+
+#include <stdio.h>
+#include <string.h>
+#include <stdlib.h>
+#include <assert.h>
+
+static char *files[] = {
+	"DerivedCoreProperties.txt",
+	"PropList.txt"
+};
+
+int
+main(int argc, char *argv[])
+{
+	FILE *f;
+	char *dir, *buf;
+	size_t dir_size, tmp_size, max_size, i, nfiles;
+
+	assert(argc == 2);
+	dir = argv[1];
+	dir_size = strlen(dir);
+
+	if(dir[dir_size-1] == '/')
+		dir_size--;
+
+	nfiles = sizeof(files)/sizeof(files[0]);
+
+	max_size = 0;
+	for(i = 0; i < nfiles; i++){
+		tmp_size = strlen(files[i]);
+		if(tmp_size > max_size)
+			max_size = tmp_size;
+	}
+	max_size += dir_size + 2;
+	buf = malloc(max_size);
+	assert(buf != NULL);
+	memcpy(buf, dir, dir_size);
+	buf[dir_size] = '/';
+
+	for(i = 0; i < sizeof(files)/sizeof(files[0]); i++){
+		memcpy(buf+dir_size+1, files[i], strlen(files[i])+1);
+		f = fopen(buf, "r");
+		assert(f != NULL);
+		fclose(f);
+
+		printf("/* Unicode file %s read from %s */\n", files[i], buf);
+	}
+
+	return 0;
+}