summaryrefslogtreecommitdiffstats
path: root/Parser/parsetok.c
blob: fc878d89d5630b0fbf1b2e4aaf0b620369e93df7 (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
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388

/* 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"
#include "graminit.h"


/* Forward */
static node *parsetok(struct tok_state *, grammar *, int, perrdetail *, int *);
static int initerr(perrdetail *err_ret, PyObject * filename);

/* Parse input coming from a string.  Return error code, print some errors. */
node *
PyParser_ParseString(const char *s, grammar *g, int start, perrdetail *err_ret)
{
    return PyParser_ParseStringFlagsFilename(s, NULL, g, start, err_ret, 0);
}

node *
PyParser_ParseStringFlags(const char *s, grammar *g, int start,
                          perrdetail *err_ret, int flags)
{
    return PyParser_ParseStringFlagsFilename(s, NULL,
                                             g, start, err_ret, flags);
}

node *
PyParser_ParseStringFlagsFilename(const char *s, const char *filename,
                          grammar *g, int start,
                          perrdetail *err_ret, int flags)
{
    int iflags = flags;
    return PyParser_ParseStringFlagsFilenameEx(s, filename, g, start,
                                               err_ret, &iflags);
}

node *
PyParser_ParseStringObject(const char *s, PyObject *filename,
                           grammar *g, int start,
                           perrdetail *err_ret, int *flags)
{
    struct tok_state *tok;
    int exec_input = start == file_input;

    if (initerr(err_ret, filename) < 0)
        return NULL;

    if (*flags & PyPARSE_IGNORE_COOKIE)
        tok = PyTokenizer_FromUTF8(s, exec_input);
    else
        tok = PyTokenizer_FromString(s, exec_input);
    if (tok == NULL) {
        err_ret->error = PyErr_Occurred() ? E_DECODE : E_NOMEM;
        return NULL;
    }

#ifndef PGEN
    Py_INCREF(err_ret->filename);
    tok->filename = err_ret->filename;
#endif
    return parsetok(tok, g, start, err_ret, flags);
}

node *
PyParser_ParseStringFlagsFilenameEx(const char *s, const char *filename_str,
                          grammar *g, int start,
                          perrdetail *err_ret, int *flags)
{
    node *n;
    PyObject *filename = NULL;
#ifndef PGEN
    if (filename_str != NULL) {
        filename = PyUnicode_DecodeFSDefault(filename_str);
        if (filename == NULL) {
            err_ret->error = E_ERROR;
            return NULL;
        }
    }
#endif
    n = PyParser_ParseStringObject(s, filename, g, start, err_ret, flags);
#ifndef PGEN
    Py_XDECREF(filename);
#endif
    return n;
}

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

node *
PyParser_ParseFile(FILE *fp, const char *filename, grammar *g, int start,
                   const char *ps1, const char *ps2,
                   perrdetail *err_ret)
{
    return PyParser_ParseFileFlags(fp, filename, NULL,
                                   g, start, ps1, ps2, err_ret, 0);
}

node *
PyParser_ParseFileFlags(FILE *fp, const char *filename, const char *enc,
                        grammar *g, int start,
                        const char *ps1, const char *ps2,
                        perrdetail *err_ret, int flags)
{
    int iflags = flags;
    return PyParser_ParseFileFlagsEx(fp, filename, enc, g, start, ps1,
                                     ps2, err_ret, &iflags);
}

node *
PyParser_ParseFileObject(FILE *fp, PyObject *filename,
                         const char *enc, grammar *g, int start,
                         const char *ps1, const char *ps2,
                         perrdetail *err_ret, int *flags)
{
    struct tok_state *tok;

    if (initerr(err_ret, filename) < 0)
        return NULL;

    if ((tok = PyTokenizer_FromFile(fp, enc, ps1, ps2)) == NULL) {
        err_ret->error = E_NOMEM;
        return NULL;
    }
#ifndef PGEN
    Py_INCREF(err_ret->filename);
    tok->filename = err_ret->filename;
#endif
    return parsetok(tok, g, start, err_ret, flags);
}

node *
PyParser_ParseFileFlagsEx(FILE *fp, const char *filename,
                          const char *enc, grammar *g, int start,
                          const char *ps1, const char *ps2,
                          perrdetail *err_ret, int *flags)
{
    node *n;
    PyObject *fileobj = NULL;
#ifndef PGEN
    if (filename != NULL) {
        fileobj = PyUnicode_DecodeFSDefault(filename);
        if (fileobj == NULL) {
            err_ret->error = E_ERROR;
            return NULL;
        }
    }
#endif
    n = PyParser_ParseFileObject(fp, fileobj, enc, g,
                                 start, ps1, ps2, err_ret, flags);
#ifndef PGEN
    Py_XDECREF(fileobj);
#endif
    return n;
}

#ifdef PY_PARSER_REQUIRES_FUTURE_KEYWORD
#if 0
static const char with_msg[] =
"%s:%d: Warning: 'with' will become a reserved keyword in Python 2.6\n";

static const char as_msg[] =
"%s:%d: Warning: 'as' will become a reserved keyword in Python 2.6\n";

static void
warn(const char *msg, const char *filename, int lineno)
{
    if (filename == NULL)
        filename = "<string>";
    PySys_WriteStderr(msg, filename, lineno);
}
#endif
#endif

/* 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,
         int *flags)
{
    parser_state *ps;
    node *n;
    int started = 0;
    int col_offset;

    if ((ps = PyParser_New(g, start)) == NULL) {
        err_ret->error = E_NOMEM;
        PyTokenizer_Free(tok);
        return NULL;
    }
#ifdef PY_PARSER_REQUIRES_FUTURE_KEYWORD
    if (*flags & PyPARSE_BARRY_AS_BDFL)
        ps->p_flags |= CO_FUTURE_BARRY_AS_BDFL;
#endif

    for (;;) {
        char *a, *b;
        int type;
        size_t len;
        char *str;
        col_offset = -1;

        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;
            /* Add the right number of dedent tokens,
               except if a certain flag is given --
               codeop.py uses this. */
            if (tok->indent &&
                !(*flags & PyPARSE_DONT_IMPLY_DEDENT))
            {
                tok->pendin = -tok->indent;
                tok->indent = 0;
            }
        }
        else
            started = 1;
        len = (a != NULL && b != NULL) ? b - a : 0;
        str = (char *) PyObject_MALLOC(len + 1);
        if (str == NULL) {
            err_ret->error = E_NOMEM;
            break;
        }
        if (len > 0)
            strncpy(str, a, len);
        str[len] = '\0';

#ifdef PY_PARSER_REQUIRES_FUTURE_KEYWORD
        if (type == NOTEQUAL) {
            if (!(ps->p_flags & CO_FUTURE_BARRY_AS_BDFL) &&
                            strcmp(str, "!=")) {
                PyObject_FREE(str);
                err_ret->error = E_SYNTAX;
                break;
            }
            else if ((ps->p_flags & CO_FUTURE_BARRY_AS_BDFL) &&
                            strcmp(str, "<>")) {
                PyObject_FREE(str);
                err_ret->expected = NOTEQUAL;
                err_ret->error = E_SYNTAX;
                break;
            }
        }
#endif
        if (a != NULL && a >= tok->line_start) {
            col_offset = Py_SAFE_DOWNCAST(a - tok->line_start,
                                          intptr_t, int);
        }
        else {
            col_offset = -1;
        }

        if ((err_ret->error =
             PyParser_AddToken(ps, (int)type, str,
                               tok->lineno, col_offset,
                               &(err_ret->expected))) != E_OK) {
            if (err_ret->error != E_DONE) {
                PyObject_FREE(str);
                err_ret->token = type;
            }
            break;
        }
    }

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

#ifndef PGEN
        /* Check that the source for a single input statement really
           is a single statement by looking at what is left in the
           buffer after parsing.  Trailing whitespace and comments
           are OK.  */
        if (start == single_input) {
            char *cur = tok->cur;
            char c = *tok->cur;

            for (;;) {
                while (c == ' ' || c == '\t' || c == '\n' || c == '\014')
                    c = *++cur;

                if (!c)
                    break;

                if (c != '#') {
                    err_ret->error = E_BADSINGLE;
                    PyNode_Free(n);
                    n = NULL;
                    break;
                }

                /* Suck up comment. */
                while (c && c != '\n')
                    c = *++cur;
            }
        }
#endif
    }
    else
        n = NULL;

#ifdef PY_PARSER_REQUIRES_FUTURE_KEYWORD
    *flags = ps->p_flags;
#endif
    PyParser_Delete(ps);

    if (n == NULL) {
        if (tok->done == E_EOF)
            err_ret->error = E_EOF;
        err_ret->lineno = tok->lineno;
        if (tok->buf != NULL) {
            size_t len;
            assert(tok->cur - tok->buf < INT_MAX);
            /* if we've managed to parse a token, point the offset to its start,
             * else use the current reading position of the tokenizer
             */
            err_ret->offset = col_offset != -1 ? col_offset + 1 : ((int)(tok->cur - tok->buf));
            len = tok->inp - tok->buf;
            err_ret->text = (char *) PyObject_MALLOC(len + 1);
            if (err_ret->text != NULL) {
                if (len > 0)
                    strncpy(err_ret->text, tok->buf, len);
                err_ret->text[len] = '\0';
            }
        }
    } else if (tok->encoding != NULL) {
        /* 'nodes->n_str' uses PyObject_*, while 'tok->encoding' was
         * allocated using PyMem_
         */
        node* r = PyNode_New(encoding_decl);
        if (r)
            r->n_str = PyObject_MALLOC(strlen(tok->encoding)+1);
        if (!r || !r->n_str) {
            err_ret->error = E_NOMEM;
            if (r)
                PyObject_FREE(r);
            n = NULL;
            goto done;
        }
        strcpy(r->n_str, tok->encoding);
        PyMem_FREE(tok->encoding);
        tok->encoding = NULL;
        r->n_nchildren = 1;
        r->n_child = n;
        n = r;
    }

done:
    PyTokenizer_Free(tok);

    return n;
}

static int
initerr(perrdetail *err_ret, PyObject *filename)
{
    err_ret->error = E_OK;
    err_ret->lineno = 0;
    err_ret->offset = 0;
    err_ret->text = NULL;
    err_ret->token = -1;
    err_ret->expected = -1;
#ifndef PGEN
    if (filename) {
        Py_INCREF(filename);
        err_ret->filename = filename;
    }
    else {
        err_ret->filename = PyUnicode_FromString("<string>");
        if (err_ret->filename == NULL) {
            err_ret->error = E_ERROR;
            return -1;
        }
    }
#endif
    return 0;
}