Merged revisions 61952-61953 via svnmerge from

svn+ssh://pythondev@svn.python.org/python/trunk

........
  r61952 | mark.dickinson | 2008-03-26 22:41:36 +0100 (Wed, 26 Mar 2008) | 2 lines

  Typo: "objects reference count" -> "object's reference count"
........
  r61953 | christian.heimes | 2008-03-26 23:01:37 +0100 (Wed, 26 Mar 2008) | 4 lines

  Patch #2477: Added from __future__ import unicode_literals

  The new PyParser_*Ex() functions are based on Neal's suggestion and initial patch. The new __future__ feature makes all '' and r'' unicode strings. b'' and br'' stay (byte) strings.
........
This commit is contained in:
Christian Heimes 2008-03-26 22:34:47 +00:00
parent 9edef04c95
commit 4d6ec85a02
11 changed files with 92 additions and 30 deletions

View file

@ -35,7 +35,7 @@ static stmt_ty ast_for_classdef(struct compiling *, const node *, asdl_seq *);
static expr_ty ast_for_call(struct compiling *, const node *, expr_ty);
static PyObject *parsenumber(const char *);
static PyObject *parsestr(const node *n, const char *encoding, int *bytesmode);
static PyObject *parsestr(struct compiling *, const node *n, int *bytesmode);
static PyObject *parsestrplus(struct compiling *, const node *n,
int *bytesmode);
@ -3191,14 +3191,13 @@ decode_unicode(const char *s, size_t len, int rawmode, const char *encoding)
* parsestr parses it, and returns the decoded Python string object.
*/
static PyObject *
parsestr(const node *n, const char *encoding, int *bytesmode)
parsestr(struct compiling *c, const node *n, int *bytesmode)
{
size_t len;
const char *s = STR(n);
int quote = Py_CHARMASK(*s);
int rawmode = 0;
int need_encoding;
if (isalpha(quote)) {
if (quote == 'b' || quote == 'B') {
quote = *++s;
@ -3233,7 +3232,7 @@ parsestr(const node *n, const char *encoding, int *bytesmode)
}
}
if (!*bytesmode && !rawmode) {
return decode_unicode(s, len, rawmode, encoding);
return decode_unicode(s, len, rawmode, c->c_encoding);
}
if (*bytesmode) {
/* Disallow non-ascii characters (but not escapes) */
@ -3246,28 +3245,27 @@ parsestr(const node *n, const char *encoding, int *bytesmode)
}
}
}
need_encoding = (!*bytesmode && encoding != NULL &&
strcmp(encoding, "utf-8") != 0 &&
strcmp(encoding, "iso-8859-1") != 0);
need_encoding = (!*bytesmode && c->c_encoding != NULL &&
strcmp(c->c_encoding, "utf-8") != 0 &&
strcmp(c->c_encoding, "iso-8859-1") != 0);
if (rawmode || strchr(s, '\\') == NULL) {
if (need_encoding) {
PyObject *v, *u = PyUnicode_DecodeUTF8(s, len, NULL);
if (u == NULL || !*bytesmode)
return u;
v = PyUnicode_AsEncodedString(u, encoding, NULL);
v = PyUnicode_AsEncodedString(u, c->c_encoding, NULL);
Py_DECREF(u);
return v;
} else if (*bytesmode) {
return PyString_FromStringAndSize(s, len);
} else if (strcmp(encoding, "utf-8") == 0) {
} else if (strcmp(c->c_encoding, "utf-8") == 0) {
return PyUnicode_FromStringAndSize(s, len);
} else {
return PyUnicode_DecodeLatin1(s, len, NULL);
}
}
return PyString_DecodeEscape(s, len, NULL, 1,
need_encoding ? encoding : NULL);
need_encoding ? c->c_encoding : NULL);
}
/* Build a Python string object out of a STRING+ atom. This takes care of
@ -3280,13 +3278,13 @@ parsestrplus(struct compiling *c, const node *n, int *bytesmode)
PyObject *v;
int i;
REQ(CHILD(n, 0), STRING);
v = parsestr(CHILD(n, 0), c->c_encoding, bytesmode);
v = parsestr(c, CHILD(n, 0), bytesmode);
if (v != NULL) {
/* String literal concatenation */
for (i = 1; i < NCH(n); i++) {
PyObject *s;
int subbm = 0;
s = parsestr(CHILD(n, i), c->c_encoding, &subbm);
s = parsestr(c, CHILD(n, i), &subbm);
if (s == NULL)
goto onError;
if (*bytesmode != subbm) {

View file

@ -35,6 +35,8 @@ future_check_features(PyFutureFeatures *ff, stmt_ty s, const char *filename)
continue;
} else if (strcmp(feature, FUTURE_PRINT_FUNCTION) == 0) {
continue;
} else if (strcmp(feature, FUTURE_UNICODE_LITERALS) == 0) {
continue;
} else if (strcmp(feature, "braces") == 0) {
PyErr_SetString(PyExc_SyntaxError,
"not a chance");

View file

@ -821,12 +821,13 @@ parse_source_module(const char *pathname, FILE *fp)
{
PyCodeObject *co = NULL;
mod_ty mod;
PyCompilerFlags flags;
PyArena *arena = PyArena_New();
if (arena == NULL)
return NULL;
mod = PyParser_ASTFromFile(fp, pathname, NULL,
Py_file_input, 0, 0, 0,
Py_file_input, 0, 0, &flags,
NULL, arena);
if (mod) {
co = PyAST_Compile(mod, pathname, NULL, arena);

View file

@ -1563,11 +1563,12 @@ Py_SymtableString(const char *str, const char *filename, int start)
{
struct symtable *st;
mod_ty mod;
PyCompilerFlags flags;
PyArena *arena = PyArena_New();
if (arena == NULL)
return NULL;
mod = PyParser_ASTFromString(str, filename, start, NULL, arena);
mod = PyParser_ASTFromString(str, filename, start, &flags, arena);
if (mod == NULL) {
PyArena_Free(arena);
return NULL;
@ -1584,10 +1585,16 @@ PyParser_ASTFromString(const char *s, const char *filename, int start,
{
mod_ty mod;
perrdetail err;
node *n = PyParser_ParseStringFlagsFilename(s, filename,
int iflags;
iflags = PARSER_FLAGS(flags);
node *n = PyParser_ParseStringFlagsFilenameEx(s, filename,
&_PyParser_Grammar, start, &err,
PARSER_FLAGS(flags));
&iflags);
if (n) {
if (flags) {
flags->cf_flags |= iflags & PyCF_MASK;
}
mod = PyAST_FromNode(n, flags, filename, arena);
PyNode_Free(n);
return mod;
@ -1606,10 +1613,16 @@ PyParser_ASTFromFile(FILE *fp, const char *filename, const char* enc,
{
mod_ty mod;
perrdetail err;
node *n = PyParser_ParseFileFlags(fp, filename, enc,
int iflags;
iflags = PARSER_FLAGS(flags);
node *n = PyParser_ParseFileFlagsEx(fp, filename, enc,
&_PyParser_Grammar,
start, ps1, ps2, &err, PARSER_FLAGS(flags));
start, ps1, ps2, &err, &iflags);
if (n) {
if (flags) {
flags->cf_flags |= iflags & PyCF_MASK;
}
mod = PyAST_FromNode(n, flags, filename, arena);
PyNode_Free(n);
return mod;