-/* PSPP - computes sample statistics.
- Copyright (C) 1997-9, 2000, 2005 Free Software Foundation, Inc.
+/* PSPP - a program for statistical analysis.
+ Copyright (C) 1997-9, 2000, 2005, 2009, 2010 Free Software Foundation, Inc.
- 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 2 of the
- License, or (at your option) any later version.
+ 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.
+ 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, write to the Free Software
- Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
- 02110-1301, USA. */
+ along with this program. If not, see <http://www.gnu.org/licenses/>. */
/*
This file is concerned with the definition of the PSPP syntax, NOT the
*/
#include <config.h>
-#include "identifier.h"
+#include "data/identifier.h"
#include <assert.h>
#include <string.h>
-#include <libpspp/assertion.h>
+#include <unictype.h>
+#include <unistr.h>
+
+#include "libpspp/assertion.h"
+#include "libpspp/cast.h"
+#include "libpspp/i18n.h"
+#include "libpspp/message.h"
+
+#include "gl/c-ctype.h"
+
+#include "gettext.h"
+#define _(msgid) gettext (msgid)
+
+/* Tokens. */
+
+/* Returns TYPE as a string, e.g. "ID" for T_ID. */
+const char *
+token_type_to_name (enum token_type type)
+{
+ switch (type)
+ {
+#define TOKEN_TYPE(TYPE) case T_##TYPE: return #TYPE;
+ TOKEN_TYPES
+#undef TOKEN_TYPE
+ case TOKEN_N_TYPES:
+ default:
+ return "unknown token type";
+ }
+}
+
+/* Returns an ASCII string that yields TOKEN if it appeared in a syntax file,
+ as a statically allocated constant string. This function returns NULL for
+ tokens that don't have any fixed string representation, such as identifier
+ and number tokens. */
+const char *
+token_type_to_string (enum token_type token)
+{
+ switch (token)
+ {
+ case T_ID:
+ case T_POS_NUM:
+ case T_NEG_NUM:
+ case T_STRING:
+ case T_STOP:
+ return NULL;
+
+ case T_ENDCMD:
+ return ".";
+
+ case T_PLUS:
+ return "+";
+
+ case T_DASH:
+ return "-";
+
+ case T_ASTERISK:
+ return "*";
+
+ case T_SLASH:
+ return "/";
+
+ case T_EQUALS:
+ return "=";
+
+ case T_LPAREN:
+ return "(";
+
+ case T_RPAREN:
+ return ")";
+
+ case T_LBRACK:
+ return "[";
+
+ case T_RBRACK:
+ return "]";
+
+ case T_COMMA:
+ return ",";
+
+ case T_AND:
+ return "AND";
+
+ case T_OR:
+ return "OR";
+
+ case T_NOT:
+ return "NOT";
+
+ case T_EQ:
+ return "EQ";
+
+ case T_GE:
+ return ">=";
+
+ case T_GT:
+ return ">";
+
+ case T_LE:
+ return "<=";
+
+ case T_LT:
+ return "<";
+
+ case T_NE:
+ return "~=";
+
+ case T_ALL:
+ return "ALL";
+
+ case T_BY:
+ return "BY";
+
+ case T_TO:
+ return "TO";
+
+ case T_WITH:
+ return "WITH";
+
+ case T_EXP:
+ return "**";
+
+ case TOKEN_N_TYPES:
+ NOT_REACHED ();
+ }
+
+ NOT_REACHED ();
+}
/* Recognizing identifiers. */
-/* Returns true if C may be the first character in an
+static bool
+is_ascii_id1 (unsigned char c)
+{
+ return c_isalpha (c) || c == '@' || c == '#' || c == '$';
+}
+
+static bool
+is_ascii_idn (unsigned char c)
+{
+ return is_ascii_id1 (c) || isdigit (c) || c == '.' || c == '_';
+}
+
+/* Returns true if C may be the first byte in an identifier in the current
+ locale.
+
+ (PSPP is transitioning to using Unicode internally for syntax, so please
+ use lex_uc_is_id1() instead, if possible.) */
+bool
+lex_is_id1 (char c)
+{
+ return is_ascii_id1 (c) || (unsigned char) c >= 128;
+}
+
+/* Returns true if C may be a byte in an identifier other than the first.
+
+ (PSPP is transitioning to using Unicode internally for syntax, so please
+ use lex_uc_is_idn() instead, if possible.) */
+bool
+lex_is_idn (char c)
+{
+ return is_ascii_idn (c) || (unsigned char) c >= 128;
+}
+
+/* Returns true if Unicode code point UC may be the first character in an
identifier in the current locale. */
bool
-lex_is_id1 (char c_)
+lex_uc_is_id1 (ucs4_t uc)
{
- unsigned char c = c_;
- return isalpha (c) || c == '@' || c == '#' || c == '$';
+ return is_ascii_id1 (uc) || (uc >= 0x80 && uc_is_property_id_start (uc));
}
+/* Returns true if Unicode code point UC may be a character in an identifier
+ other than the first. */
+bool
+lex_uc_is_idn (ucs4_t uc)
+{
+ return (is_ascii_id1 (uc) || isdigit (uc) || uc == '.' || uc == '_'
+ || (uc >= 0x80 && uc_is_property_id_continue (uc)));
+}
-/* Returns true if C may be a character in an identifier other
- than the first. */
+/* Returns true if Unicode code point UC is a space that separates tokens. */
bool
-lex_is_idn (char c_)
+lex_uc_is_space (ucs4_t uc)
{
- unsigned char c = c_;
- return lex_is_id1 (c) || isdigit (c) || c == '.' || c == '_';
+ /* These are all of the Unicode characters in category Zs, Zl, or Zp. */
+ return (uc == ' ' || (uc <= 0x000d && uc >= 0x0009)
+ || (uc >= 0x80
+ && (uc == 0xa0 || uc == 0x85 || uc == 0x1680 || uc == 0x180e
+ || (uc >= 0x2000 && uc <= 0x200a)
+ || uc == 0x2028 || uc == 0x2029 || uc == 0x202f
+ || uc == 0x205f || uc == 0x3000)));
}
+
/* Returns the length of the longest prefix of STRING that forms
a valid identifier. Returns zero if STRING does not begin
with a valid identifier. */
Keywords match if one of the following is true: KEYWORD and
TOKEN are identical, or TOKEN is at least 3 characters long
- and those characters are identical to KEYWORD. */
+ and those characters are identical to KEYWORD. (Letters that
+ differ only in case are considered identical.)
+
+ KEYWORD must be ASCII, but TOKEN may be ASCII or UTF-8. */
bool
lex_id_match (struct substring keyword, struct substring token)
+{
+ return lex_id_match_n (keyword, token, 3);
+}
+
+/* Returns true if TOKEN is a case-insensitive match for at least
+ the first N characters of KEYWORD.
+
+ KEYWORD must be ASCII, but TOKEN may be ASCII or UTF-8. */
+bool
+lex_id_match_n (struct substring keyword, struct substring token, size_t n)
{
size_t token_len = ss_length (token);
size_t keyword_len = ss_length (keyword);
- if (token_len >= 3 && token_len < keyword_len)
+ if (token_len >= n && token_len < keyword_len)
return ss_equals_case (ss_head (keyword, token_len), token);
else
return ss_equals_case (keyword, token);
/* Returns true if TOKEN is representable as a keyword. */
bool
-lex_is_keyword (int token)
+lex_is_keyword (enum token_type token)
{
const struct keyword *kw;
for (kw = keywords; kw < &keywords[keyword_cnt]; kw++)
/* Returns the name for the given keyword token type. */
const char *
-lex_id_name (int token)
+lex_id_name (enum token_type token)
{
const struct keyword *kw;
projects / pspp-builds.git / blobdiff