view mercurial/cext/dirs.c @ 35616:706aa203b396

fileset: add a lightweight file filtering language

This patch was inspired by one that Jun Wu authored for the fb-experimental
repo, to avoid using matcher for efficiency[1].  We want a way to specify what
files will be converted to LFS at commit time.  And per discussion, we also want
to specify what files to skip, text diff, or merge in another config option.
The current `lfs.threshold` config option could not satisfy complex needs.  I'm
putting it in a core package because Augie floated the idea of also using it for
narrow and sparse.

Yuya suggested farming out to fileset.parse(), which added support for more
symbols.  The only fileset element not supported here is 'negate'.  (List isn't
supported by filesets either.)  I also changed the 'always' token to the 'all()'
predicate for consistency, and introduced 'none()' to improve readability in a
future tracked file based config.  The extension operator was changed from '.'
to '**', to match how recursive path globs are specified.  Finally, I changed
the path matcher from '/' to 'path:' at Yuya's suggestion, for consistency with
matcher.  Unfortunately, ':' is currently reserved in filesets, so this has to
be quoted to be processed as a string instead of a symbol[2].  We should
probably revisit that, because it's seriously ugly.  But it's only used by an
experimental extension, and I think using a file based config for LFS may drive
some more tweaks, so I'm settling for this for now.

I reserved all of the glob characters in fileset except '.' and '_' for the
extension test because those are likely valid extension characters.

Sample filter settings:

  all()                        # everything
  size(">20MB")                # larger than 20MB
  !**.txt                      # except for .txt files
  **.zip | **.tar.gz | **.7z   # some types of compressed files
  "path:bin"                   # files under "bin" in the project root

[1] https://www.mercurial-scm.org/pipermail/mercurial-devel/2017-December/109387.html
[2] https://www.mercurial-scm.org/pipermail/mercurial-devel/2018-January/109729.html

/*
 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);
}