tokenizer.c

python s60 1.4.5版本的源代码

/* Portions Copyright (c) 2005 Nokia Corporation */

/* Tokenizer implementation */

#include "python_globals.h"

#include "pgenheaders.h"

#include <ctype.h>

#include "tokenizer.h"
#include "errcode.h"

extern char *PyOS_Readline(char *);
/* Return malloc'ed string including trailing \n;
   empty malloc'ed string for EOF;
   NULL if interrupted */

/* Don't ever change this -- it would break the portability of Python code */
#define TABSIZE 8

/* Convert a possibly signed character to a nonnegative int */
/* XXX This assumes characters are 8 bits wide */
#ifdef __CHAR_UNSIGNED__
#define Py_CHARMASK(c)		(c)
#else
#define Py_CHARMASK(c)		((c) & 0xff)
#endif

/* Forward */
static struct tok_state *tok_new(void);
static int tok_nextc(struct tok_state *tok);
static void tok_backup(struct tok_state *tok, int c);

/* Token names */

const char *const _PyParser_TokenNames[] = {
	"ENDMARKER",
	"NAME",
	"NUMBER",
	"STRING",
	"NEWLINE",
	"INDENT",
	"DEDENT",
	"LPAR",
	"RPAR",
	"LSQB",
	"RSQB",
	"COLON",
	"COMMA",
	"SEMI",
	"PLUS",
	"MINUS",
	"STAR",
	"SLASH",
	"VBAR",
	"AMPER",
	"LESS",
	"GREATER",
	"EQUAL",
	"DOT",
	"PERCENT",
	"BACKQUOTE",
	"LBRACE",
	"RBRACE",
	"EQEQUAL",
	"NOTEQUAL",
	"LESSEQUAL",
	"GREATEREQUAL",
	"TILDE",
	"CIRCUMFLEX",
	"LEFTSHIFT",
	"RIGHTSHIFT",
	"DOUBLESTAR",
	"PLUSEQUAL",
	"MINEQUAL",
	"STAREQUAL",
	"SLASHEQUAL",
	"PERCENTEQUAL",
	"AMPEREQUAL",
	"VBAREQUAL",
	"CIRCUMFLEXEQUAL",
	"LEFTSHIFTEQUAL",
	"RIGHTSHIFTEQUAL",
	"DOUBLESTAREQUAL",
	"DOUBLESLASH",
	"DOUBLESLASHEQUAL",
	/* This table must match the #defines in token.h! */
	"OP",
	"<ERRORTOKEN>",
	"<N_TOKENS>"
};


/* Create and initialize a new tok_state structure */

static struct tok_state *
tok_new(void)
{
	struct tok_state *tok = PyMem_NEW(struct tok_state, 1);
	if (tok == NULL)
		return NULL;
	tok->buf = tok->cur = tok->end = tok->inp = tok->start = NULL;
	tok->done = E_OK;
	tok->fp = NULL;
	tok->tabsize = TABSIZE;
	tok->indent = 0;
	tok->indstack[0] = 0;
	tok->atbol = 1;
	tok->pendin = 0;
	tok->prompt = tok->nextprompt = NULL;
	tok->lineno = 0;
	tok->level = 0;
	tok->filename = NULL;
	tok->altwarning = 0;
	tok->alterror = 0;
	tok->alttabsize = 1;
	tok->altindstack[0] = 0;
	return tok;
}


/* Set up tokenizer for string */

struct tok_state *
PyTokenizer_FromString(char *str)
{
	struct tok_state *tok = tok_new();
	if (tok == NULL)
		return NULL;
	tok->buf = tok->cur = tok->end = tok->inp = str;
	return tok;
}


/* Set up tokenizer for file */

struct tok_state *
PyTokenizer_FromFile(FILE *fp, char *ps1, char *ps2)
{
	struct tok_state *tok = tok_new();
	if (tok == NULL)
		return NULL;
	if ((tok->buf = PyMem_NEW(char, BUFSIZ)) == NULL) {
		PyMem_DEL(tok);
		return NULL;
	}
	tok->cur = tok->inp = tok->buf;
	tok->end = tok->buf + BUFSIZ;
	tok->fp = fp;
	tok->prompt = ps1;
	tok->nextprompt = ps2;
	return tok;
}


/* Free a tok_state structure */

void
PyTokenizer_Free(struct tok_state *tok)
{
	if (tok->fp != NULL && tok->buf != NULL)
		PyMem_DEL(tok->buf);
	PyMem_DEL(tok);
}


/* Get next char, updating state; error code goes into tok->done */

static int
tok_nextc(register struct tok_state *tok)
{
	for (;;) {
		if (tok->cur != tok->inp) {
			return Py_CHARMASK(*tok->cur++); /* Fast path */
		}
		if (tok->done != E_OK)
			return EOF;
		if (tok->fp == NULL) {
			char *end = strchr(tok->inp, '\n');
			if (end != NULL)
				end++;
			else {
				end = strchr(tok->inp, '\0');
				if (end == tok->inp) {
					tok->done = E_EOF;
					return EOF;
				}
			}
			if (tok->start == NULL)
				tok->buf = tok->cur;
			tok->lineno++;
			tok->inp = end;
			return Py_CHARMASK(*tok->cur++);
		}
		if (tok->prompt != NULL) {
			char *new = PyOS_Readline(tok->prompt);
			if (tok->nextprompt != NULL)
				tok->prompt = tok->nextprompt;
			if (new == NULL)
				tok->done = E_INTR;
			else if (*new == '\0') {
				PyMem_FREE(new);
				tok->done = E_EOF;
			}
			else if (tok->start != NULL) {
				size_t start = tok->start - tok->buf;
				size_t oldlen = tok->cur - tok->buf;
				size_t newlen = oldlen + strlen(new);
				char *buf = tok->buf;
				PyMem_RESIZE(buf, char, newlen+1);
				tok->lineno++;
				if (buf == NULL) {
					PyMem_DEL(tok->buf);
					tok->buf = NULL;
					PyMem_FREE(new);
					tok->done = E_NOMEM;
					return EOF;
				}
				tok->buf = buf;
				tok->cur = tok->buf + oldlen;
				strcpy(tok->buf + oldlen, new);
				PyMem_FREE(new);
				tok->inp = tok->buf + newlen;
				tok->end = tok->inp + 1;
				tok->start = tok->buf + start;
			}
			else {
				tok->lineno++;
				if (tok->buf != NULL)
					PyMem_DEL(tok->buf);
				tok->buf = new;
				tok->cur = tok->buf;
				tok->inp = strchr(tok->buf, '\0');
				tok->end = tok->inp + 1;
			}
		}
		else {
			int done = 0;
			int cur = 0;
			char *pt;
			if (tok->start == NULL) {
				if (tok->buf == NULL) {
					tok->buf = PyMem_NEW(char, BUFSIZ);
					if (tok->buf == NULL) {
						tok->done = E_NOMEM;
						return EOF;
					}
					tok->end = tok->buf + BUFSIZ;
				}
				if (fgets(tok->buf, (int)(tok->end - tok->buf),
					  tok->fp) == NULL) {
					tok->done = E_EOF;
					done = 1;
				}
				else {
					tok->done = E_OK;
					tok->inp = strchr(tok->buf, '\0');
					done = tok->inp[-1] == '\n';
				}
			}
			else {
				cur = tok->cur - tok->buf;
				if (feof(tok->fp)) {
					tok->done = E_EOF;
					done = 1;
				}
				else
					tok->done = E_OK;
			}
			tok->lineno++;
			/* Read until '\n' or EOF */
			while (!done) {
				int curstart = tok->start == NULL ? -1 :
					       tok->start - tok->buf;
				int curvalid = tok->inp - tok->buf;
				int newsize = curvalid + BUFSIZ;
				char *newbuf = tok->buf;
				PyMem_RESIZE(newbuf, char, newsize);
				if (newbuf == NULL) {
					tok->done = E_NOMEM;
					tok->cur = tok->inp;
					return EOF;
				}
				tok->buf = newbuf;
				tok->inp = tok->buf + curvalid;
				tok->end = tok->buf + newsize;
				tok->start = curstart < 0 ? NULL :
					     tok->buf + curstart;
				if (fgets(tok->inp,
					       (int)(tok->end - tok->inp),
					       tok->fp) == NULL) {
					/* Last line does not end in \n,
					   fake one */
					strcpy(tok->inp, "\n");
				}
				tok->inp = strchr(tok->inp, '\0');
				done = tok->inp[-1] == '\n';
			}
			tok->cur = tok->buf + cur;
#ifndef macintosh
			/* replace "\r\n" with "\n" */
			/* For Mac we leave the \r, giving a syntax error */
			pt = tok->inp - 2;
			if (pt >= tok->buf && *pt == '\r') {
				*pt++ = '\n';
				*pt = '\0';
				tok->inp = pt;
			}
#endif
		}
		if (tok->done != E_OK) {
			if (tok->prompt != NULL)
				PySys_WriteStderr("\n");
			tok->cur = tok->inp;
			return EOF;
		}
	}
	/*NOTREACHED*/
}


/* Back-up one character */

static void
tok_backup(register struct tok_state *tok, register int c)
{
	if (c != EOF) {
		if (--tok->cur < tok->buf)
			Py_FatalError("tok_backup: begin of buffer");
		if (*tok->cur != c)
			*tok->cur = c;
	}
}


/* Return the token corresponding to a single character */

DL_EXPORT(int)
PyToken_OneChar(int c)
{
	switch (c) {
	case '(':	return LPAR;
	case ')':	return RPAR;
	case '[':	return LSQB;
	case ']':	return RSQB;
	case ':':	return COLON;
	case ',':	return COMMA;
	case ';':	return SEMI;
	case '+':	return PLUS;
	case '-':	return MINUS;
	case '*':	return STAR;
	case '/':	return SLASH;
	case '|':	return VBAR;
	case '&':	return AMPER;
	case '<':	return LESS;
	case '>':	return GREATER;
	case '=':	return EQUAL;
	case '.':	return DOT;
	case '%':	return PERCENT;
	case '`':	return BACKQUOTE;
	case '{':	return LBRACE;
	case '}':	return RBRACE;
	case '^':	return CIRCUMFLEX;
	case '~':	return TILDE;
	default:	return OP;
	}
}


DL_EXPORT(int)
PyToken_TwoChars(int c1, int c2)
{
	switch (c1) {
	case '=':
		switch (c2) {
		case '=':	return EQEQUAL;
		}
		break;
	case '!':
		switch (c2) {
		case '=':	return NOTEQUAL;
		}
		break;
	case '<':
		switch (c2) {
		case '>':	return NOTEQUAL;
		case '=':	return LESSEQUAL;
		case '<':	return LEFTSHIFT;
		}
		break;
	case '>':
		switch (c2) {
		case '=':	return GREATEREQUAL;
		case '>':	return RIGHTSHIFT;
		}
		break;
	case '+':
		switch (c2) {
		case '=':	return PLUSEQUAL;
		}
		break;
	case '-':
		switch (c2) {
		case '=':	return MINEQUAL;
		}
		break;
	case '*':
		switch (c2) {
		case '*':	return DOUBLESTAR;
		case '=':	return STAREQUAL;
		}
		break;
	case '/':
		switch (c2) {
		case '/':	return DOUBLESLASH;
		case '=':	return SLASHEQUAL;
		}
		break;
	case '|':
		switch (c2) {
		case '=':	return VBAREQUAL;
		}
		break;
	case '%':
		switch (c2) {
		case '=':	return PERCENTEQUAL;
		}
		break;
	case '&':
		switch (c2) {
		case '=':	return AMPEREQUAL;
		}
		break;
	case '^':
		switch (c2) {
		case '=':	return CIRCUMFLEXEQUAL;
		}
		break;
	}
	return OP;
}

DL_EXPORT(int)
PyToken_ThreeChars(int c1, int c2, int c3)
{
	switch (c1) {
	case '<':
		switch (c2) {
		case '<':
			switch (c3) {
			case '=':
				return LEFTSHIFTEQUAL;
			}
			break;
		}
		break;
	case '>':
		switch (c2) {
		case '>':
			switch (c3) {
			case '=':
				return RIGHTSHIFTEQUAL;
			}
			break;
		}
		break;