##// END OF EJS Templates
encoding: define an enum that specifies what normcase does to ASCII strings...
encoding: define an enum that specifies what normcase does to ASCII strings For C code we don't want to pay the cost of calling into a Python function for the common case of ASCII filenames. However, while on most POSIX platforms we normalize filenames by lowercasing them, on Windows we uppercase them. We define an enum here indicating the direction that filenames should be normalized as. Some platforms (notably Cygwin) have more complicated normalization behavior -- we add a case for that too. In upcoming patches we'll also define a fallback function that is called if the string has non-ASCII bytes. This enum will be replicated in the C code to make foldmaps. There's unfortunately no nice way to avoid that -- we can't have encoding import parsers because of import cycles. One way might be to have parsers import encoding, but accessing Python modules from C code is just awkward. The name 'normcasespecs' was chosen to indicate that this is merely an integer that specifies a behavior, not a function. The name was pluralized since in upcoming patches we'll introduce 'normcasespec' which will be one of these values.

File last commit:

r24486:1a9efc31 default
r24593:f473a1fe default
Show More
dirs.c
307 lines | 6.5 KiB | text/x-c | CLexer
/*
dirs.c - dynamic directory diddling for dirstates
Copyright 2013 Facebook
This software may be used and distributed according to the terms of
the GNU General Public License, incorporated herein by reference.
*/
#define PY_SSIZE_T_CLEAN
#include <Python.h>
#include <string.h>
#include "util.h"
/*
* This is a multiset of directory names, built from the files that
* appear in a dirstate or manifest.
*
* A few implementation notes:
*
* We modify Python integers for refcounting, but those integers are
* never visible to Python code.
*
* We mutate strings in-place, but leave them immutable once they can
* be seen by Python code.
*/
typedef struct {
PyObject_HEAD
PyObject *dict;
} dirsObject;
static inline Py_ssize_t _finddir(PyObject *path, Py_ssize_t pos)
{
const char *s = PyString_AS_STRING(path);
const char *ret = strchr(s + pos, '/');
return (ret != NULL) ? (ret - s) : -1;
}
static int _addpath(PyObject *dirs, PyObject *path)
{
char *cpath = PyString_AS_STRING(path);
Py_ssize_t len = PyString_GET_SIZE(path);
Py_ssize_t pos = -1;
PyObject *key = NULL;
int ret = -1;
while ((pos = _finddir(path, pos + 1)) != -1) {
PyObject *val;
/* It's likely that every prefix already has an entry
in our dict. Try to avoid allocating and
deallocating a string for each prefix we check. */
if (key != NULL)
((PyStringObject *)key)->ob_shash = -1;
else if (pos != 0) {
/* pos >= 1, which means that len >= 2. This is
guaranteed to produce a non-interned string. */
key = PyString_FromStringAndSize(cpath, len);
if (key == NULL)
goto bail;
} else {
/* pos == 0, which means we need to increment the dir
count for the empty string. We need to make sure we
don't muck around with interned strings, so throw it
away later. */
key = PyString_FromString("");
if (key == NULL)
goto bail;
}
PyString_GET_SIZE(key) = pos;
PyString_AS_STRING(key)[pos] = '\0';
val = PyDict_GetItem(dirs, key);
if (val != NULL) {
PyInt_AS_LONG(val) += 1;
if (pos != 0)
PyString_AS_STRING(key)[pos] = '/';
else
key = NULL;
continue;
}
/* Force Python to not reuse a small shared int. */
val = PyInt_FromLong(0x1eadbeef);
if (val == NULL)
goto bail;
PyInt_AS_LONG(val) = 1;
ret = PyDict_SetItem(dirs, key, val);
Py_DECREF(val);
if (ret == -1)
goto bail;
if (pos != 0)
PyString_AS_STRING(key)[pos] = '/';
else
key = NULL;
Py_CLEAR(key);
}
ret = 0;
bail:
Py_XDECREF(key);
return ret;
}
static int _delpath(PyObject *dirs, PyObject *path)
{
Py_ssize_t pos = -1;
PyObject *key = NULL;
int ret = -1;
while ((pos = _finddir(path, pos + 1)) != -1) {
PyObject *val;
key = PyString_FromStringAndSize(PyString_AS_STRING(path), pos);
if (key == NULL)
goto bail;
val = PyDict_GetItem(dirs, key);
if (val == NULL) {
PyErr_SetString(PyExc_ValueError,
"expected a value, found none");
goto bail;
}
if (--PyInt_AS_LONG(val) <= 0 &&
PyDict_DelItem(dirs, key) == -1)
goto bail;
Py_CLEAR(key);
}
ret = 0;
bail:
Py_XDECREF(key);
return ret;
}
static int dirs_fromdict(PyObject *dirs, PyObject *source, char skipchar)
{
PyObject *key, *value;
Py_ssize_t pos = 0;
while (PyDict_Next(source, &pos, &key, &value)) {
if (!PyString_Check(key)) {
PyErr_SetString(PyExc_TypeError, "expected string key");
return -1;
}
if (skipchar) {
if (!dirstate_tuple_check(value)) {
PyErr_SetString(PyExc_TypeError,
"expected a dirstate tuple");
return -1;
}
if (((dirstateTupleObject *)value)->state == skipchar)
continue;
}
if (_addpath(dirs, key) == -1)
return -1;
}
return 0;
}
static int dirs_fromiter(PyObject *dirs, PyObject *source)
{
PyObject *iter, *item = NULL;
int ret;
iter = PyObject_GetIter(source);
if (iter == NULL)
return -1;
while ((item = PyIter_Next(iter)) != NULL) {
if (!PyString_Check(item)) {
PyErr_SetString(PyExc_TypeError, "expected string");
break;
}
if (_addpath(dirs, item) == -1)
break;
Py_CLEAR(item);
}
ret = PyErr_Occurred() ? -1 : 0;
Py_DECREF(iter);
Py_XDECREF(item);
return ret;
}
/*
* Calculate a refcounted set of directory names for the files in a
* dirstate.
*/
static int dirs_init(dirsObject *self, PyObject *args)
{
PyObject *dirs = NULL, *source = NULL;
char skipchar = 0;
int ret = -1;
self->dict = NULL;
if (!PyArg_ParseTuple(args, "|Oc:__init__", &source, &skipchar))
return -1;
dirs = PyDict_New();
if (dirs == NULL)
return -1;
if (source == NULL)
ret = 0;
else if (PyDict_Check(source))
ret = dirs_fromdict(dirs, source, skipchar);
else if (skipchar)
PyErr_SetString(PyExc_ValueError,
"skip character is only supported "
"with a dict source");
else
ret = dirs_fromiter(dirs, source);
if (ret == -1)
Py_XDECREF(dirs);
else
self->dict = dirs;
return ret;
}
PyObject *dirs_addpath(dirsObject *self, PyObject *args)
{
PyObject *path;
if (!PyArg_ParseTuple(args, "O!:addpath", &PyString_Type, &path))
return NULL;
if (_addpath(self->dict, path) == -1)
return NULL;
Py_RETURN_NONE;
}
static PyObject *dirs_delpath(dirsObject *self, PyObject *args)
{
PyObject *path;
if (!PyArg_ParseTuple(args, "O!:delpath", &PyString_Type, &path))
return NULL;
if (_delpath(self->dict, path) == -1)
return NULL;
Py_RETURN_NONE;
}
static int dirs_contains(dirsObject *self, PyObject *value)
{
return PyString_Check(value) ? PyDict_Contains(self->dict, value) : 0;
}
static void dirs_dealloc(dirsObject *self)
{
Py_XDECREF(self->dict);
PyObject_Del(self);
}
static PyObject *dirs_iter(dirsObject *self)
{
return PyObject_GetIter(self->dict);
}
static PySequenceMethods dirs_sequence_methods;
static PyMethodDef dirs_methods[] = {
{"addpath", (PyCFunction)dirs_addpath, METH_VARARGS, "add a path"},
{"delpath", (PyCFunction)dirs_delpath, METH_VARARGS, "remove a path"},
{NULL} /* Sentinel */
};
static PyTypeObject dirsType = { PyObject_HEAD_INIT(NULL) };
void dirs_module_init(PyObject *mod)
{
dirs_sequence_methods.sq_contains = (objobjproc)dirs_contains;
dirsType.tp_name = "parsers.dirs";
dirsType.tp_new = PyType_GenericNew;
dirsType.tp_basicsize = sizeof(dirsObject);
dirsType.tp_dealloc = (destructor)dirs_dealloc;
dirsType.tp_as_sequence = &dirs_sequence_methods;
dirsType.tp_flags = Py_TPFLAGS_DEFAULT;
dirsType.tp_doc = "dirs";
dirsType.tp_iter = (getiterfunc)dirs_iter;
dirsType.tp_methods = dirs_methods;
dirsType.tp_init = (initproc)dirs_init;
if (PyType_Ready(&dirsType) < 0)
return;
Py_INCREF(&dirsType);
PyModule_AddObject(mod, "dirs", (PyObject *)&dirsType);
}