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.
diff --git a/Python/ast.c b/Python/ast.c
index 1fc2324..bc91805 100644
--- a/Python/ast.c
+++ b/Python/ast.c
@@ -18,6 +18,7 @@
/* Data structure used internally */
struct compiling {
char *c_encoding; /* source encoding */
+ int c_future_unicode; /* __future__ unicode literals flag */
PyArena *c_arena; /* arena for allocating memeory */
const char *c_filename; /* filename */
};
@@ -36,7 +37,7 @@
static expr_ty ast_for_call(struct compiling *, const node *, expr_ty);
static PyObject *parsenumber(const char *);
-static PyObject *parsestr(const char *s, const char *encoding);
+static PyObject *parsestr(struct compiling *, const char *);
static PyObject *parsestrplus(struct compiling *, const node *n);
#ifndef LINENO
@@ -198,6 +199,7 @@
} else {
c.c_encoding = NULL;
}
+ c.c_future_unicode = flags && flags->cf_flags & CO_FUTURE_UNICODE_LITERALS;
c.c_arena = arena;
c.c_filename = filename;
@@ -3247,13 +3249,13 @@
* parsestr parses it, and returns the decoded Python string object.
*/
static PyObject *
-parsestr(const char *s, const char *encoding)
+parsestr(struct compiling *c, const char *s)
{
size_t len;
int quote = Py_CHARMASK(*s);
int rawmode = 0;
int need_encoding;
- int unicode = 0;
+ int unicode = c->c_future_unicode;
if (isalpha(quote) || quote == '_') {
if (quote == 'u' || quote == 'U') {
@@ -3262,6 +3264,7 @@
}
if (quote == 'b' || quote == 'B') {
quote = *++s;
+ unicode = 0;
}
if (quote == 'r' || quote == 'R') {
quote = *++s;
@@ -3293,12 +3296,12 @@
}
#ifdef Py_USING_UNICODE
if (unicode || Py_UnicodeFlag) {
- return decode_unicode(s, len, rawmode, encoding);
+ return decode_unicode(s, len, rawmode, c->c_encoding);
}
#endif
- need_encoding = (encoding != NULL &&
- strcmp(encoding, "utf-8") != 0 &&
- strcmp(encoding, "iso-8859-1") != 0);
+ need_encoding = (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) {
#ifndef Py_USING_UNICODE
@@ -3310,7 +3313,7 @@
PyObject *v, *u = PyUnicode_DecodeUTF8(s, len, NULL);
if (u == NULL)
return NULL;
- v = PyUnicode_AsEncodedString(u, encoding, NULL);
+ v = PyUnicode_AsEncodedString(u, c->c_encoding, NULL);
Py_DECREF(u);
return v;
#endif
@@ -3320,7 +3323,7 @@
}
return PyString_DecodeEscape(s, len, NULL, unicode,
- need_encoding ? encoding : NULL);
+ need_encoding ? c->c_encoding : NULL);
}
/* Build a Python string object out of a STRING atom. This takes care of
@@ -3333,11 +3336,11 @@
PyObject *v;
int i;
REQ(CHILD(n, 0), STRING);
- if ((v = parsestr(STR(CHILD(n, 0)), c->c_encoding)) != NULL) {
+ if ((v = parsestr(c, STR(CHILD(n, 0)))) != NULL) {
/* String literal concatenation */
for (i = 1; i < NCH(n); i++) {
PyObject *s;
- s = parsestr(STR(CHILD(n, i)), c->c_encoding);
+ s = parsestr(c, STR(CHILD(n, i)));
if (s == NULL)
goto onError;
if (PyString_Check(v) && PyString_Check(s)) {
diff --git a/Python/future.c b/Python/future.c
index 267e1b7..2c6aaa2 100644
--- a/Python/future.c
+++ b/Python/future.c
@@ -35,6 +35,8 @@
ff->ff_features |= CO_FUTURE_WITH_STATEMENT;
} else if (strcmp(feature, FUTURE_PRINT_FUNCTION) == 0) {
ff->ff_features |= CO_FUTURE_PRINT_FUNCTION;
+ } else if (strcmp(feature, FUTURE_UNICODE_LITERALS) == 0) {
+ ff->ff_features |= CO_FUTURE_UNICODE_LITERALS;
} else if (strcmp(feature, "braces") == 0) {
PyErr_SetString(PyExc_SyntaxError,
"not a chance");
diff --git a/Python/import.c b/Python/import.c
index ecbec15..95cd20d 100644
--- a/Python/import.c
+++ b/Python/import.c
@@ -818,11 +818,12 @@
{
PyCodeObject *co = NULL;
mod_ty mod;
+ PyCompilerFlags flags;
PyArena *arena = PyArena_New();
if (arena == NULL)
return NULL;
- mod = PyParser_ASTFromFile(fp, pathname, Py_file_input, 0, 0, 0,
+ mod = PyParser_ASTFromFile(fp, pathname, Py_file_input, 0, 0, &flags,
NULL, arena);
if (mod) {
co = PyAST_Compile(mod, pathname, NULL, arena);
diff --git a/Python/pythonrun.c b/Python/pythonrun.c
index 226fee3..423aae1 100644
--- a/Python/pythonrun.c
+++ b/Python/pythonrun.c
@@ -774,8 +774,11 @@
#define PARSER_FLAGS(flags) \
((flags) ? ((((flags)->cf_flags & PyCF_DONT_IMPLY_DEDENT) ? \
PyPARSE_DONT_IMPLY_DEDENT : 0) \
- | ((flags)->cf_flags & CO_FUTURE_PRINT_FUNCTION ? \
- PyPARSE_PRINT_IS_FUNCTION : 0)) : 0)
+ | (((flags)->cf_flags & CO_FUTURE_PRINT_FUNCTION) ? \
+ PyPARSE_PRINT_IS_FUNCTION : 0) \
+ | (((flags)->cf_flags & CO_FUTURE_UNICODE_LITERALS) ? \
+ PyPARSE_UNICODE_LITERALS : 0) \
+ ) : 0)
#endif
int
@@ -1390,11 +1393,12 @@
{
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;
@@ -1411,10 +1415,16 @@
{
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;
@@ -1432,9 +1442,15 @@
{
mod_ty mod;
perrdetail err;
- node *n = PyParser_ParseFileFlags(fp, filename, &_PyParser_Grammar,
- start, ps1, ps2, &err, PARSER_FLAGS(flags));
+ int iflags;
+
+ iflags = PARSER_FLAGS(flags);
+ node *n = PyParser_ParseFileFlagsEx(fp, filename, &_PyParser_Grammar,
+ 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;