aboutsummaryrefslogtreecommitdiff
blob: 5f51f6adbdb6e95828caa292cab409433633723f (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
/***********************************************************
Copyright (c) 2000, BeOpen.com.
Copyright (c) 1995-2000, Corporation for National Research Initiatives.
Copyright (c) 1990-1995, Stichting Mathematisch Centrum.
All rights reserved.

See the file "Misc/COPYRIGHT" for information on usage and
redistribution of this file, and for a DISCLAIMER OF ALL WARRANTIES.
******************************************************************/

/* Parser-tokenizer link implementation */

#include "pgenheaders.h"
#include "tokenizer.h"
#include "node.h"
#include "grammar.h"
#include "parser.h"
#include "parsetok.h"
#include "errcode.h"

int Py_TabcheckFlag;


/* Forward */
static node *parsetok(struct tok_state *, grammar *, int, perrdetail *);

/* Parse input coming from a string.  Return error code, print some errors. */

node *
PyParser_ParseString(char *s, grammar *g, int start, perrdetail *err_ret)
{
	struct tok_state *tok;

	err_ret->error = E_OK;
	err_ret->filename = NULL;
	err_ret->lineno = 0;
	err_ret->offset = 0;
	err_ret->text = NULL;
	err_ret->token = -1;
	err_ret->expected = -1;

	if ((tok = PyTokenizer_FromString(s)) == NULL) {
		err_ret->error = E_NOMEM;
		return NULL;
	}

	if (Py_TabcheckFlag || Py_VerboseFlag) {
		tok->filename = "<string>";
		tok->altwarning = (tok->filename != NULL);
		if (Py_TabcheckFlag >= 2)
			tok->alterror++;
	}

	return parsetok(tok, g, start, err_ret);
}


/* Parse input coming from a file.  Return error code, print some errors. */

node *
PyParser_ParseFile(FILE *fp, char *filename, grammar *g, int start,
		   char *ps1, char *ps2, perrdetail *err_ret)
{
	struct tok_state *tok;

	err_ret->error = E_OK;
	err_ret->filename = filename;
	err_ret->lineno = 0;
	err_ret->offset = 0;
	err_ret->text = NULL;

	if ((tok = PyTokenizer_FromFile(fp, ps1, ps2)) == NULL) {
		err_ret->error = E_NOMEM;
		return NULL;
	}
	if (Py_TabcheckFlag || Py_VerboseFlag) {
		tok->filename = filename;
		tok->altwarning = (filename != NULL);
		if (Py_TabcheckFlag >= 2)
			tok->alterror++;
	}


	return parsetok(tok, g, start, err_ret);
}

/* Parse input coming from the given tokenizer structure.
   Return error code. */

static node *
parsetok(struct tok_state *tok, grammar *g, int start, perrdetail *err_ret)
{
	parser_state *ps;
	node *n;
	int started = 0;

	if ((ps = PyParser_New(g, start)) == NULL) {
		fprintf(stderr, "no mem for new parser\n");
		err_ret->error = E_NOMEM;
		return NULL;
	}

	for (;;) {
		char *a, *b;
		int type;
		size_t len;
		char *str;

		type = PyTokenizer_Get(tok, &a, &b);
		if (type == ERRORTOKEN) {
			err_ret->error = tok->done;
			break;
		}
		if (type == ENDMARKER && started) {
			type = NEWLINE; /* Add an extra newline */
			started = 0;
		}
		else
			started = 1;
		len = b - a; /* XXX this may compute NULL - NULL */
		str = PyMem_NEW(char, len + 1);
		if (str == NULL) {
			fprintf(stderr, "no mem for next token\n");
			err_ret->error = E_NOMEM;
			break;
		}
		if (len > 0)
			strncpy(str, a, len);
		str[len] = '\0';
		if ((err_ret->error =
		     PyParser_AddToken(ps, (int)type, str, tok->lineno,
				       &(err_ret->expected))) != E_OK) {
			if (err_ret->error != E_DONE)
				PyMem_DEL(str);
			break;
		}
	}

	if (err_ret->error == E_DONE) {
		n = ps->p_tree;
		ps->p_tree = NULL;
	}
	else
		n = NULL;

	PyParser_Delete(ps);

	if (n == NULL) {
		if (tok->lineno <= 1 && tok->done == E_EOF)
			err_ret->error = E_EOF;
		err_ret->lineno = tok->lineno;
		err_ret->offset = tok->cur - tok->buf;
		if (tok->buf != NULL) {
			size_t len = tok->inp - tok->buf;
			err_ret->text = PyMem_NEW(char, len + 1);
			if (err_ret->text != NULL) {
				if (len > 0)
					strncpy(err_ret->text, tok->buf, len);
				err_ret->text[len] = '\0';
			}
		}
	}

	PyTokenizer_Free(tok);

	return n;
}