view mercurial/cext/dirs.c @ 36426:23d12524a202

http: drop custom http client logic Eight and a half years ago, as my starter bug on code.google.com, I investigated a mysterious "broken pipe" error from seemingly random clients[0]. That investigation revealed a tragic story: the Python standard library's httplib was (and remains) barely functional. During large POSTs, if a server responds early with an error (even a permission denied error!) the client only notices that the server closed the connection and everything breaks. Such server behavior is implicitly legal under RFC 2616 (the latest HTTP RFC as of when I was last working on this), and my understanding is that later RFCs have made it explicitly legal to respond early with any status code outside the 2xx range. I embarked, probably foolishly, on a journey to write a new http library with better overall behavior. The http library appears to work well in most cases, but it can get confused in the presence of proxies, and it depends on select(2) which limits its utility if a lot of file descriptors are open. I haven't touched the http library in almost two years, and in the interim the Python community has discovered a better way[1] of writing network code. In theory some day urllib3 will have its own home-grown http library built on h11[2], or we could do that. Either way, it's time to declare our current confusingly-named "http2" client logic and move on. I do hope to revisit this some day: it's still garbage that we can't even respond with a 401 or 403 without reading the entire POST body from the client, but the goalposts on writing a new http client library have moved substantially. We're almost certainly better off just switching to requests and eventually picking up their http fixes than trying to live with something that realistically only we'll ever use. Another approach would be to write an adapter so that Mercurial can use pycurl if it's installed. Neither of those approaches seem like they should be investigated prior to a release of Mercurial that works on Python 3: that's where the mindshare is going to be for any improvements to the state of the http client art. 0: http://web.archive.org/web/20130501031801/http://code.google.com/p/support/issues/detail?id=2716 1: http://sans-io.readthedocs.io/ 2: https://github.com/njsmith/h11 Differential Revision: https://phab.mercurial-scm.org/D2444
author Augie Fackler <augie@google.com>
date Sun, 25 Feb 2018 23:51:32 -0500
parents b90e8da190da
children d8e55c0c642c
line wrap: on
line source

/*
 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 "util.h"

#ifdef IS_PY3K
#define PYLONG_VALUE(o) ((PyLongObject *)o)->ob_digit[1]
#else
#define PYLONG_VALUE(o) PyInt_AS_LONG(o)
#endif

/*
 * 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(const char *path, Py_ssize_t pos)
{
	while (pos != -1) {
		if (path[pos] == '/')
			break;
		pos -= 1;
	}

	return pos;
}

static int _addpath(PyObject *dirs, PyObject *path)
{
	const char *cpath = PyBytes_AS_STRING(path);
	Py_ssize_t pos = PyBytes_GET_SIZE(path);
	PyObject *key = NULL;
	int ret = -1;

	/* This loop is super critical for performance. That's why we inline
	* access to Python structs instead of going through a supported API.
	* The implementation, therefore, is heavily dependent on CPython
	* implementation details. We also commit violations of the Python
	* "protocol" such as mutating immutable objects. But since we only
	* mutate objects created in this function or in other well-defined
	* locations, the references are known so these violations should go
	* unnoticed. The code for adjusting the length of a PyBytesObject is
	* essentially a minimal version of _PyBytes_Resize. */
	while ((pos = _finddir(cpath, 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)
			((PyBytesObject *)key)->ob_shash = -1;
		else {
			/* Force Python to not reuse a small shared string. */
			key = PyBytes_FromStringAndSize(cpath,
							 pos < 2 ? 2 : pos);
			if (key == NULL)
				goto bail;
		}
		/* Py_SIZE(o) refers to the ob_size member of the struct. Yes,
		* assigning to what looks like a function seems wrong. */
		Py_SIZE(key) = pos;
		((PyBytesObject *)key)->ob_sval[pos] = '\0';

		val = PyDict_GetItem(dirs, key);
		if (val != NULL) {
			PYLONG_VALUE(val) += 1;
			break;
		}

		/* Force Python to not reuse a small shared int. */
#ifdef IS_PY3K
		val = PyLong_FromLong(0x1eadbeef);
#else
		val = PyInt_FromLong(0x1eadbeef);
#endif

		if (val == NULL)
			goto bail;

		PYLONG_VALUE(val) = 1;
		ret = PyDict_SetItem(dirs, key, val);
		Py_DECREF(val);
		if (ret == -1)
			goto bail;
		Py_CLEAR(key);
	}
	ret = 0;

bail:
	Py_XDECREF(key);

	return ret;
}

static int _delpath(PyObject *dirs, PyObject *path)
{
	char *cpath = PyBytes_AS_STRING(path);
	Py_ssize_t pos = PyBytes_GET_SIZE(path);
	PyObject *key = NULL;
	int ret = -1;

	while ((pos = _finddir(cpath, pos - 1)) != -1) {
		PyObject *val;

		key = PyBytes_FromStringAndSize(cpath, 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 (--PYLONG_VALUE(val) <= 0) {
			if (PyDict_DelItem(dirs, key) == -1)
				goto bail;
		} else
			break;
		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 (!PyBytes_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 (!PyBytes_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", &PyBytes_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", &PyBytes_Type, &path))
		return NULL;

	if (_delpath(self->dict, path) == -1)
		return NULL;

	Py_RETURN_NONE;
}

static int dirs_contains(dirsObject *self, PyObject *value)
{
	return PyBytes_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 = { PyVarObject_HEAD_INIT(NULL, 0) };

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);
}