X-Git-Url: https://pintos-os.org/cgi-bin/gitweb.cgi?a=blobdiff_plain;f=src%2Flanguage%2Flexer%2Flexer.c;h=8b3f2a48d00474811a09c090f8a82d1b75ed7546;hb=6b003fcaaf12c21fda3d44580154b54c54c6cd54;hp=1c9542d78ed54ccf5271811b5cc27be54337aeae;hpb=9b94efd7513afdb12a6023024e00e50801532fee;p=pspp-builds.git

diff --git a/src/language/lexer/lexer.c b/src/language/lexer/lexer.c
index 1c9542d7..8b3f2a48 100644
--- a/src/language/lexer/lexer.c
+++ b/src/language/lexer/lexer.c
@@ -1,5 +1,5 @@
 /* PSPP - a program for statistical analysis.
-   Copyright (C) 1997-9, 2000, 2006 Free Software Foundation, Inc.
+   Copyright (C) 1997-9, 2000, 2006, 2009 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
@@ -17,7 +17,8 @@
 #include <config.h>
 #include "lexer.h"
 #include <libpspp/message.h>
-#include <ctype.h>
+#include <c-ctype.h>
+#include <c-strtod.h>
 #include <errno.h>
 #include <limits.h>
 #include <math.h>
@@ -187,7 +188,7 @@ lex_get (struct lexer *lexer)
   for (;;)
     {
       /* Skip whitespace. */
-	  while (isspace ((unsigned char) *lexer->prog))
+	  while (c_isspace ((unsigned char) *lexer->prog))
 	    lexer->prog++;
 
 	  if (*lexer->prog)
@@ -244,10 +245,10 @@ lex_get (struct lexer *lexer)
 	    if (*lexer->prog == '-')
 	      {
 		ds_put_char (&lexer->tokstr, *lexer->prog++);
-		while (isspace ((unsigned char) *lexer->prog))
+		while (c_isspace ((unsigned char) *lexer->prog))
 		  lexer->prog++;
 
-		if (!isdigit ((unsigned char) *lexer->prog) && *lexer->prog != '.')
+		if (!c_isdigit ((unsigned char) *lexer->prog) && *lexer->prog != '.')
 		  {
 		    lexer->token = '-';
 		    break;
@@ -258,12 +259,12 @@ lex_get (struct lexer *lexer)
               lexer->token = T_POS_NUM;
 
 	    /* Parse the number, copying it into tokstr. */
-	    while (isdigit ((unsigned char) *lexer->prog))
+	    while (c_isdigit ((unsigned char) *lexer->prog))
 	      ds_put_char (&lexer->tokstr, *lexer->prog++);
 	    if (*lexer->prog == '.')
 	      {
 		ds_put_char (&lexer->tokstr, *lexer->prog++);
-		while (isdigit ((unsigned char) *lexer->prog))
+		while (c_isdigit ((unsigned char) *lexer->prog))
 		  ds_put_char (&lexer->tokstr, *lexer->prog++);
 	      }
 	    if (*lexer->prog == 'e' || *lexer->prog == 'E')
@@ -271,12 +272,12 @@ lex_get (struct lexer *lexer)
 		ds_put_char (&lexer->tokstr, *lexer->prog++);
 		if (*lexer->prog == '+' || *lexer->prog == '-')
 		  ds_put_char (&lexer->tokstr, *lexer->prog++);
-		while (isdigit ((unsigned char) *lexer->prog))
+		while (c_isdigit ((unsigned char) *lexer->prog))
 		  ds_put_char (&lexer->tokstr, *lexer->prog++);
 	      }
 
 	    /* Parse as floating point. */
-	    lexer->tokval = strtod (ds_cstr (&lexer->tokstr), &tail);
+	    lexer->tokval = c_strtod (ds_cstr (&lexer->tokstr), &tail);
 	    if (*tail)
 	      {
 		msg (SE, _("%s does not form a valid number."),
@@ -295,6 +296,7 @@ lex_get (struct lexer *lexer)
 	  break;
 
 	case '(': case ')': case ',': case '=': case '+': case '/':
+        case '[': case ']':
 	  lexer->token = *lexer->prog++;
 	  break;
 
@@ -382,10 +384,10 @@ lex_get (struct lexer *lexer)
             }
           else
             {
-              if (isgraph ((unsigned char) *lexer->prog))
-                msg (SE, _("Bad character in input: `%c'."), *lexer->prog++);
-              else
-                msg (SE, _("Bad character in input: `\\%o'."), *lexer->prog++);
+              unsigned char c = *lexer->prog++;
+              char *c_name = xasprintf (c_isgraph (c) ? "%c" : "\\%o", c);
+              msg (SE, _("Bad character in input: `%s'."), c_name);
+              free (c_name);
               continue;
             }
         }
@@ -690,7 +692,7 @@ lex_look_ahead (struct lexer *lexer)
 
       for (;;)
 	{
-	  while (isspace ((unsigned char) *lexer->prog))
+	  while (c_isspace ((unsigned char) *lexer->prog))
 	    lexer->prog++;
 	  if (*lexer->prog)
 	    break;
@@ -865,7 +867,7 @@ lex_preprocess_line (struct string *line,
   if (syntax == GETL_BATCH)
     {
       int first = ds_first (line);
-      *line_starts_command = !isspace (first);
+      *line_starts_command = !c_isspace (first);
       if (first == '+' || first == '-')
         *ds_data (line) = ' ';
     }
@@ -950,7 +952,7 @@ lex_token_representation (struct lexer *lexer)
 	char *sp, *dp;
 
 	for (sp = ds_cstr (&lexer->tokstr); sp < ds_end (&lexer->tokstr); sp++)
-	  if (!isprint ((unsigned char) *sp))
+	  if (!c_isprint ((unsigned char) *sp))
 	    {
 	      hexstring = 1;
 	      break;
@@ -1164,7 +1166,7 @@ parse_string (struct lexer *lexer, enum string_type type)
 	break;
       for (;;)
 	{
-	  while (isspace ((unsigned char) *lexer->prog))
+	  while (c_isspace ((unsigned char) *lexer->prog))
 	    lexer->prog++;
 	  if (*lexer->prog)
 	    break;
@@ -1186,7 +1188,7 @@ parse_string (struct lexer *lexer, enum string_type type)
 	break;
       for (;;)
 	{
-	  while (isspace ((unsigned char) *lexer->prog))
+	  while (c_isspace ((unsigned char) *lexer->prog))
 	    lexer->prog++;
 	  if (*lexer->prog)
 	    break;
@@ -1304,3 +1306,28 @@ lex_tokstr (const struct lexer *lexer)
 {
   return &lexer->tokstr;
 }
+
+/* If the lexer is positioned at the (pseudo)identifier S, which
+   may contain a hyphen ('-'), skips it and returns true.  Each
+   half of the identifier may be abbreviated to its first three
+   letters.
+   Otherwise, returns false. */
+bool
+lex_match_hyphenated_word (struct lexer *lexer, const char *s)
+{
+  const char *hyphen = strchr (s, '-');
+  if (hyphen == NULL)
+    return lex_match_id (lexer, s);
+  else if (lexer->token != T_ID
+	   || !lex_id_match (ss_buffer (s, hyphen - s), ss_cstr (lexer->tokid))
+	   || lex_look_ahead (lexer) != '-')
+    return false;
+  else
+    {
+      lex_get (lexer);
+      lex_force_match (lexer, '-');
+      lex_force_match_id (lexer, hyphen + 1);
+      return true;
+    }
+}
+