aboutsummaryrefslogtreecommitdiffstats
path: root/regexp/parse-unidata.awk
diff options
context:
space:
mode:
authorNIIBE Yutaka <[email protected]>2020-04-03 06:30:08 +0000
committerNIIBE Yutaka <[email protected]>2020-04-03 06:30:08 +0000
commitba247a114c75a84473c11c1484013b09fbb9bcd1 (patch)
treea76cedce73621da0142ceb7d71ae51cad8696ec3 /regexp/parse-unidata.awk
parentscd:p15: Implement do_with_keygrip and capabilities. (diff)
downloadgnupg-ba247a114c75a84473c11c1484013b09fbb9bcd1.tar.gz
gnupg-ba247a114c75a84473c11c1484013b09fbb9bcd1.zip
gpg: Add regular expression support.
* AUTHORS, COPYING.other: Update. * Makefile.am (SUBDIRS): Add regexp sub directory. * configure.ac (DISABLE_REGEX): Remove. * g10/Makefile.am (needed_libs): Add libregexp.a. * g10/trustdb.c: Remove DISABLE_REGEX support. * regexp/LICENSE, regexp/jimregexp.c, regexp/jimregexp.h, regexp/utf8.c, regexp/utf8.h: New from Jim Tcl. * regexp/UnicodeData.txt: New from Unicode. * regexp/Makefile.am, regexp/parse-unidata.awk: New. * tests/openpgp/Makefile.am: Remove DISABLE_REGEX support. * tools/Makefile.am: Remove DISABLE_REGEX support. GnuPG-bug-id: 4843 Signed-off-by: NIIBE Yutaka <[email protected]>
Diffstat (limited to 'regexp/parse-unidata.awk')
-rw-r--r--regexp/parse-unidata.awk62
1 files changed, 62 insertions, 0 deletions
diff --git a/regexp/parse-unidata.awk b/regexp/parse-unidata.awk
new file mode 100644
index 000000000..8bdc0bf8b
--- /dev/null
+++ b/regexp/parse-unidata.awk
@@ -0,0 +1,62 @@
+#
+# parse-unidata.awk - generate a table (unicode_case_mapping_upper)
+#
+# Copyright (C) 2020 g10 Code GmbH
+#
+# This file is part of GnuPG.
+#
+# GnuPG 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.
+#
+# GnuPG 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 <https://www.gnu.org/licenses/>.
+#
+
+# Parse the unicode data from:
+# https://www.unicode.org/Public/UCD/latest/ucd/UnicodeData.txt
+# to generate case mapping table
+
+BEGIN {
+ print("/* Generated from UnicodeData.txt */")
+ print("")
+ print("static const struct casemap unicode_case_mapping_upper[] = {")
+ FS = ";"
+ count = 0
+}
+
+{
+ code = strtonum(("0x" $1))
+ name = $2
+ class = $3
+ upper = $13
+ lower = $14
+ title = $15
+
+ if (code <= 0x7f) {
+ next
+ }
+ if (code > 0xffff) {
+ next
+ }
+ if ($3 !~ /^L.*/) {
+ next
+ }
+ if (upper != "") {
+ printf("\t{ 0x" tolower($1) ", 0x" tolower(upper) " },")
+ count++
+ if ((count % 4) == 0) {
+ print("")
+ }
+ }
+}
+
+END {
+ print("\n};")
+}