Parser/parsetok.c

   1 /***********************************************************
   2 Copyright 1991-1995 by Stichting Mathematisch Centrum, Amsterdam,
   3 The Netherlands.
   4
   5                         All Rights Reserved
   6
   7 Permission to use, copy, modify, and distribute this software and its
   8 documentation for any purpose and without fee is hereby granted,
   9 provided that the above copyright notice appear in all copies and that
  10 both that copyright notice and this permission notice appear in
  11 supporting documentation, and that the names of Stichting Mathematisch
  12 Centrum or CWI or Corporation for National Research Initiatives or
  13 CNRI not be used in advertising or publicity pertaining to
  14 distribution of the software without specific, written prior
  15 permission.
  16
  17 While CWI is the initial source for this software, a modified version
  18 is made available by the Corporation for National Research Initiatives
  19 (CNRI) at the Internet address ftp://ftp.python.org.
  20
  21 STICHTING MATHEMATISCH CENTRUM AND CNRI DISCLAIM ALL WARRANTIES WITH
  22 REGARD TO THIS SOFTWARE, INCLUDING ALL IMPLIED WARRANTIES OF
  23 MERCHANTABILITY AND FITNESS, IN NO EVENT SHALL STICHTING MATHEMATISCH
  24 CENTRUM OR CNRI BE LIABLE FOR ANY SPECIAL, INDIRECT OR CONSEQUENTIAL
  25 DAMAGES OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR
  26 PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER
  27 TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR
  28 PERFORMANCE OF THIS SOFTWARE.
  29
  30 ******************************************************************/
  31
  32 /* Parser-tokenizer link implementation */
  33
  34 #include "pgenheaders.h"
  35 #include "tokenizer.h"
  36 #include "node.h"
  37 #include "grammar.h"
  38 #include "parser.h"
  39 #include "parsetok.h"
  40 #include "errcode.h"
  41
  42 int Py_TabcheckFlag;
  43
  44
  45 /* Forward */
  46 static node *parsetok Py_PROTO((struct tok_state *, grammar *, int,
  47                              perrdetail *));
  48
  49 /* Parse input coming from a string.  Return error code, print some errors. */
  50
  51 node *
  52 PyParser_ParseString(s, g, start, err_ret)
  53         char *s;
  54         grammar *g;
  55         int start;
  56         perrdetail *err_ret;
  57 {
  58         struct tok_state *tok;
  59
  60         err_ret->error = E_OK;
  61         err_ret->filename = NULL;
  62         err_ret->lineno = 0;
  63         err_ret->offset = 0;
  64         err_ret->text = NULL;
  65
  66         if ((tok = PyTokenizer_FromString(s)) == NULL) {
  67                 err_ret->error = E_NOMEM;
  68                 return NULL;
  69         }
  70
  71         return parsetok(tok, g, start, err_ret);
  72 }
  73
  74
  75 /* Parse input coming from a file.  Return error code, print some errors. */
  76
  77 node *
  78 PyParser_ParseFile(fp, filename, g, start, ps1, ps2, err_ret)
  79         FILE *fp;
  80         char *filename;
  81         grammar *g;
  82         int start;
  83         char *ps1, *ps2;
  84         perrdetail *err_ret;
  85 {
  86         struct tok_state *tok;
  87
  88         err_ret->error = E_OK;
  89         err_ret->filename = filename;
  90         err_ret->lineno = 0;
  91         err_ret->offset = 0;
  92         err_ret->text = NULL;
  93
  94         if ((tok = PyTokenizer_FromFile(fp, ps1, ps2)) == NULL) {
  95                 err_ret->error = E_NOMEM;
  96                 return NULL;
  97         }
  98         if (Py_TabcheckFlag || Py_VerboseFlag) {
  99                 tok->filename = filename;
 100                 tok->altwarning = (filename != NULL);
 101                 if (Py_TabcheckFlag >= 2)
 102                         tok->alterror++;
 103         }
 104
 105 #ifdef macintosh
 106         {
 107                 int tabsize = guesstabsize(filename);
 108                 if (tabsize > 0)
 109                         tok->tabsize = tabsize;
 110         }
 111 #endif
 112
 113         return parsetok(tok, g, start, err_ret);
 114 }
 115
 116 /* Parse input coming from the given tokenizer structure.
 117    Return error code. */
 118
 119 static node *
 120 parsetok(tok, g, start, err_ret)
 121         struct tok_state *tok;
 122         grammar *g;
 123         int start;
 124         perrdetail *err_ret;
 125 {
 126         parser_state *ps;
 127         node *n;
 128         int started = 0;
 129
 130         if ((ps = PyParser_New(g, start)) == NULL) {
 131                 fprintf(stderr, "no mem for new parser\n");
 132                 err_ret->error = E_NOMEM;
 133                 return NULL;
 134         }
 135
 136         for (;;) {
 137                 char *a, *b;
 138                 int type;
 139                 int len;
 140                 char *str;
 141
 142                 type = PyTokenizer_Get(tok, &a, &b);
 143                 if (type == ERRORTOKEN) {
 144                         err_ret->error = tok->done;
 145                         break;
 146                 }
 147                 if (type == ENDMARKER && started) {
 148                         type = NEWLINE; /* Add an extra newline */
 149                         started = 0;
 150                 }
 151                 else
 152                         started = 1;
 153                 len = b - a; /* XXX this may compute NULL - NULL */
 154                 str = PyMem_NEW(char, len + 1);
 155                 if (str == NULL) {
 156                         fprintf(stderr, "no mem for next token\n");
 157                         err_ret->error = E_NOMEM;
 158                         break;
 159                 }
 160                 if (len > 0)
 161                         strncpy(str, a, len);
 162                 str[len] = '\0';
 163                 if ((err_ret->error =
 164                      PyParser_AddToken(ps, (int)type, str,
 165                                        tok->lineno)) != E_OK) {
 166                         if (err_ret->error != E_DONE)
 167                                 PyMem_DEL(str);
 168                         break;
 169                 }
 170         }
 171
 172         if (err_ret->error == E_DONE) {
 173                 n = ps->p_tree;
 174                 ps->p_tree = NULL;
 175         }
 176         else
 177                 n = NULL;
 178
 179         PyParser_Delete(ps);
 180
 181         if (n == NULL) {
 182                 if (tok->lineno <= 1 && tok->done == E_EOF)
 183                         err_ret->error = E_EOF;
 184                 err_ret->lineno = tok->lineno;
 185                 err_ret->offset = tok->cur - tok->buf;
 186                 if (tok->buf != NULL) {
 187                         int len = tok->inp - tok->buf;
 188                         err_ret->text = malloc(len + 1);
 189                         if (err_ret->text != NULL) {
 190                                 if (len > 0)
 191                                         strncpy(err_ret->text, tok->buf, len);
 192                                 err_ret->text[len] = '\0';
 193                         }
 194                 }
 195         }
 196
 197         PyTokenizer_Free(tok);
 198
 199         return n;
 200 }