c: Interpret string literals lazily

* x-c.c (P7_EOF, P7_STRING_END, P7_QUOTES, P7_QUOTE, P7_NEWLINE)
(UNICODE, IS_UNICODE, UNICODE_VALUE): Remove.
(phase7_get): Remove.
(phase7_ungetc): Remove.
(phase5_get): Use 'phase3_get' directly to extract string
literals; use 'arglist_parser_remember_literal' instead of
'arglist_parser_remember'.
(literalstring_parse): New function.
(literalstring_c): New variable.
(extract_parenthesized): Remove the
'xgettext_current_source_encoding' setting to prevent encoding
conversion around 'arglist_parser_done'.
* x-c.h (SCANNERS_C): Register 'literalstring_c' as a
literalstring_parser.
(literalstring_c): New variable declaration.

1 files changed, 61 insertions, 0 deletions

diff --git a/gettext-tools/tests/xgettext-c-19 b/gettext-tools/tests/xgettext-c-19
new file mode 100755
index 0000000..581a200
--- /dev/null
+++ b/gettext-tools/tests/xgettext-c-19
@@ -0,0 +1,61 @@
+#! /bin/sh
+. "${srcdir=.}/init.sh"; path_prepend_ . ../src
+
+# Test C support: mixing ANSI escapes, Unicode escapes, and bare
+# multibyte characters.
+
+cat <<\EOF > xg-c-19.in.c
+/* 最初のコメント */
+"最初の文字列";
+
+/* 二番目のコメント */
+gettext ("二番目の文字列");
+
+/* 三番目のコメント */
+pgettext ("\u30B3\u30F3\u30C6\u30AF\u30B9\u30C8", "\xBB\xB0\xC8\xD6\xCC\xDC\xA4\xCE\xCA\xB8\xBB\xFA\xCE\xF3");
+EOF
+
+: ${ICONV=iconv}
+iconv --from UTF-8 --to EUC-JP < xg-c-19.in.c > xg-c-19.c \
+  || { echo "Skipping test: iconv does not work for EUC-JP"; exit 77; }
+
+: ${XGETTEXT=xgettext}
+${XGETTEXT} --from-code=EUC-JP --add-comments --no-location \
+	    -o - xg-c-19.c | grep -v 'POT-Creation-Date' > xg-c-19.tmp.po \
+	    || exit 1
+LC_ALL=C tr -d '\r' < xg-c-19.tmp.po > xg-c-19.po || exit 1
+
+cat <<EOF > xg-c-19.ok
+# SOME DESCRIPTIVE TITLE.
+# Copyright (C) YEAR THE PACKAGE'S COPYRIGHT HOLDER
+# This file is distributed under the same license as the PACKAGE package.
+# FIRST AUTHOR <EMAIL@ADDRESS>, YEAR.
+#
+#, fuzzy
+msgid ""
+msgstr ""
+"Project-Id-Version: PACKAGE VERSION\n"
+"Report-Msgid-Bugs-To: \n"
+"PO-Revision-Date: YEAR-MO-DA HO:MI+ZONE\n"
+"Last-Translator: FULL NAME <EMAIL@ADDRESS>\n"
+"Language-Team: LANGUAGE <LL@li.org>\n"
+"Language: \n"
+"MIME-Version: 1.0\n"
+"Content-Type: text/plain; charset=UTF-8\n"
+"Content-Transfer-Encoding: 8bit\n"
+
+#. 二番目のコメント
+msgid "二番目の文字列"
+msgstr ""
+
+#. 三番目のコメント
+msgctxt "コンテクスト"
+msgid "三番目の文字列"
+msgstr ""
+EOF
+
+: ${DIFF=diff}
+${DIFF} xg-c-19.ok xg-c-19.po
+result=$?
+
+exit $result