From b39ab76118067fe6e7cb83afb176dcef4c936d3d Mon Sep 17 00:00:00 2001 From: Max Kellermann Date: Sat, 19 Oct 2013 15:25:32 +0200 Subject: Util/CharUtil: new library replacing g_ascii_isX() --- src/util/CharUtil.hxx | 114 ++++++++++++++++++++++++++++++++++++++++++++++++ src/util/StringUtil.cxx | 3 +- src/util/Tokenizer.cxx | 11 ++--- 3 files changed, 122 insertions(+), 6 deletions(-) create mode 100644 src/util/CharUtil.hxx (limited to 'src/util') diff --git a/src/util/CharUtil.hxx b/src/util/CharUtil.hxx new file mode 100644 index 000000000..dd964f9c3 --- /dev/null +++ b/src/util/CharUtil.hxx @@ -0,0 +1,114 @@ +/* + * Copyright (C) 2011-2013 Max Kellermann + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * + * - Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * + * - Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the + * distribution. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + * ``AS IS'' AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS + * FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE + * FOUNDATION OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, + * INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES + * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR + * SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) + * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, + * STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED + * OF THE POSSIBILITY OF SUCH DAMAGE. + */ + +#ifndef CHAR_UTIL_HPP +#define CHAR_UTIL_HPP + +constexpr +static inline bool +IsASCII(const unsigned char ch) +{ + return ch < 0x80; +} + +constexpr +static inline bool +IsASCII(const char ch) +{ + return IsASCII((unsigned char)ch); +} + +static inline bool +IsWhitespaceOrNull(const char ch) +{ + return (unsigned char)ch <= 0x20; +} + +static inline bool +IsWhitespaceNotNull(const char ch) +{ + return ch > 0 && ch <= 0x20; +} + +constexpr +static inline bool +IsPrintableASCII(char ch) +{ + return (signed char)ch >= 0x20; +} + +constexpr +static inline bool +IsDigitASCII(char ch) +{ + return ch >= '0' && ch <= '9'; +} + +constexpr +static inline bool +IsUpperAlphaASCII(char ch) +{ + return ch >= 'A' && ch <= 'Z'; +} + +constexpr +static inline bool +IsLowerAlphaASCII(char ch) +{ + return ch >= 'a' && ch <= 'z'; +} + +constexpr +static inline bool +IsAlphaASCII(char ch) +{ + return IsUpperAlphaASCII(ch) || IsLowerAlphaASCII(ch); +} + +constexpr +static inline bool +IsAlphaNumericASCII(char ch) +{ + return IsAlphaASCII(ch) || IsDigitASCII(ch); +} + +/** + * Convert the specified ASCII character (0x00..0x7f) to upper case. + * Unlike toupper(), it ignores the system locale. + */ +constexpr +static inline char +ToUpperASCII(char ch) +{ + return ch >= 'a' && ch <= 'z' + ? (ch - ('a' - 'A')) + : ch; +} + +#endif diff --git a/src/util/StringUtil.cxx b/src/util/StringUtil.cxx index 26aa7825e..048f009f5 100644 --- a/src/util/StringUtil.cxx +++ b/src/util/StringUtil.cxx @@ -18,6 +18,7 @@ */ #include "StringUtil.hxx" +#include "CharUtil.hxx" #include @@ -26,7 +27,7 @@ const char * strchug_fast(const char *p) { - while (*p != 0 && g_ascii_isspace(*p)) + while (IsWhitespaceNotNull(*p)) ++p; return p; diff --git a/src/util/Tokenizer.cxx b/src/util/Tokenizer.cxx index 726da0dd6..1c8af23fd 100644 --- a/src/util/Tokenizer.cxx +++ b/src/util/Tokenizer.cxx @@ -19,6 +19,7 @@ #include "config.h" #include "Tokenizer.hxx" +#include "CharUtil.hxx" #include "StringUtil.hxx" #include "Error.hxx" #include "Domain.hxx" @@ -33,13 +34,13 @@ static constexpr Domain tokenizer_domain("tokenizer"); static inline bool valid_word_first_char(char ch) { - return g_ascii_isalpha(ch); + return IsAlphaASCII(ch); } static inline bool valid_word_char(char ch) { - return g_ascii_isalnum(ch) || ch == '_'; + return IsAlphaNumericASCII(ch) || ch == '_'; } char * @@ -61,7 +62,7 @@ Tokenizer::NextWord(Error &error) whitespace or end-of-string */ while (*++input != 0) { - if (g_ascii_isspace(*input)) { + if (IsWhitespaceOrNull(*input)) { /* a whitespace: the word ends here */ *input = 0; /* skip all following spaces, too */ @@ -106,7 +107,7 @@ Tokenizer::NextUnquoted(Error &error) whitespace or end-of-string */ while (*++input != 0) { - if (g_ascii_isspace(*input)) { + if (IsWhitespaceOrNull(*input)) { /* a whitespace: the word ends here */ *input = 0; /* skip all following spaces, too */ @@ -170,7 +171,7 @@ Tokenizer::NextString(Error &error) line) */ ++input; - if (*input != 0 && !g_ascii_isspace(*input)) { + if (!IsWhitespaceOrNull(*input)) { error.Set(tokenizer_domain, "Space expected after closing '\"'"); return nullptr; -- cgit v1.2.3