dirstate-entry: add a `removed` property

Lets start to define and use more semantic property.

Differential Revision: https://phab.mercurial-scm.org/D10957

mercurial/cext/parsers.c

@@ -1,827 +1,837
 /*
  parsers.c - efficient content parsing
 
  Copyright 2008 Olivia Mackall <[e-mail]> and others
 
  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 <ctype.h>
 #include <stddef.h>
 #include <string.h>
 
 #include "bitmanipulation.h"
 #include "charencode.h"
 #include "util.h"
 
 #ifdef IS_PY3K
 /* The mapping of Python types is meant to be temporary to get Python
  * 3 to compile. We should remove this once Python 3 support is fully
  * supported and proper types are used in the extensions themselves. */
 #define PyInt_Check PyLong_Check
 #define PyInt_FromLong PyLong_FromLong
 #define PyInt_FromSsize_t PyLong_FromSsize_t
 #define PyInt_AsLong PyLong_AsLong
 #endif
 
 static const char *const versionerrortext = "Python minor version mismatch";
 
 static const int dirstate_v1_from_p2 = -2;
 
 static PyObject *dict_new_presized(PyObject *self, PyObject *args)
 {
 	Py_ssize_t expected_size;
 
 	if (!PyArg_ParseTuple(args, "n:make_presized_dict", &expected_size)) {
 		return NULL;
 	}
 
 	return _dict_new_presized(expected_size);
 }
 
 static inline dirstateTupleObject *make_dirstate_tuple(char state, int mode,
                                                        int size, int mtime)
 {
 	dirstateTupleObject *t =
 	    PyObject_New(dirstateTupleObject, &dirstateTupleType);
 	if (!t) {
 		return NULL;
 	}
 	t->state = state;
 	t->mode = mode;
 	t->size = size;
 	t->mtime = mtime;
 	return t;
 }
 
 static PyObject *dirstate_tuple_new(PyTypeObject *subtype, PyObject *args,
                                     PyObject *kwds)
 {
 	/* We do all the initialization here and not a tp_init function because
 	 * dirstate_tuple is immutable. */
 	dirstateTupleObject *t;
 	char state;
 	int size, mode, mtime;
 	if (!PyArg_ParseTuple(args, "ciii", &state, &mode, &size, &mtime)) {
 		return NULL;
 	}
 
 	t = (dirstateTupleObject *)subtype->tp_alloc(subtype, 1);
 	if (!t) {
 		return NULL;
 	}
 	t->state = state;
 	t->mode = mode;
 	t->size = size;
 	t->mtime = mtime;
 
 	return (PyObject *)t;
 }
 
 static void dirstate_tuple_dealloc(PyObject *o)
 {
 	PyObject_Del(o);
 }
 
 static Py_ssize_t dirstate_tuple_length(PyObject *o)
 {
 	return 4;
 }
 
 static PyObject *dirstate_tuple_item(PyObject *o, Py_ssize_t i)
 {
 	dirstateTupleObject *t = (dirstateTupleObject *)o;
 	switch (i) {
 	case 0:
 		return PyBytes_FromStringAndSize(&t->state, 1);
 	case 1:
 		return PyInt_FromLong(t->mode);
 	case 2:
 		return PyInt_FromLong(t->size);
 	case 3:
 		return PyInt_FromLong(t->mtime);
 	default:
 		PyErr_SetString(PyExc_IndexError, "index out of range");
 		return NULL;
 	}
 }
 
 static PySequenceMethods dirstate_tuple_sq = {
     dirstate_tuple_length, /* sq_length */
     0,                     /* sq_concat */
     0,                     /* sq_repeat */
     dirstate_tuple_item,   /* sq_item */
     0,                     /* sq_ass_item */
     0,                     /* sq_contains */
     0,                     /* sq_inplace_concat */
     0                      /* sq_inplace_repeat */
 };
 
 static PyObject *dirstatetuple_v1_state(dirstateTupleObject *self)
 {
 	return PyBytes_FromStringAndSize(&self->state, 1);
 };
 
 static PyObject *dirstatetuple_v1_mode(dirstateTupleObject *self)
 {
 	return PyInt_FromLong(self->mode);
 };
 
 static PyObject *dirstatetuple_v1_size(dirstateTupleObject *self)
 {
 	return PyInt_FromLong(self->size);
 };
 
 static PyObject *dirstatetuple_v1_mtime(dirstateTupleObject *self)
 {
 	return PyInt_FromLong(self->mtime);
 };
 
 static PyMethodDef dirstatetuple_methods[] = {
     {"v1_state", (PyCFunction)dirstatetuple_v1_state, METH_NOARGS,
      "return a \"state\" suitable for v1 serialization"},
     {"v1_mode", (PyCFunction)dirstatetuple_v1_mode, METH_NOARGS,
      "return a \"mode\" suitable for v1 serialization"},
     {"v1_size", (PyCFunction)dirstatetuple_v1_size, METH_NOARGS,
      "return a \"size\" suitable for v1 serialization"},
     {"v1_mtime", (PyCFunction)dirstatetuple_v1_mtime, METH_NOARGS,
      "return a \"mtime\" suitable for v1 serialization"},
     {NULL} /* Sentinel */
 };
 
 static PyObject *dirstatetuple_get_state(dirstateTupleObject *self)
 {
 	return PyBytes_FromStringAndSize(&self->state, 1);
 };
 
 static PyObject *dirstatetuple_get_merged(dirstateTupleObject *self)
 {
 	if (self->state == 'm') {
 		Py_RETURN_TRUE;
 	} else {
 		Py_RETURN_FALSE;
 	}
 };
 
 static PyObject *dirstatetuple_get_from_p2(dirstateTupleObject *self)
 {
 	if (self->size == dirstate_v1_from_p2) {
 		Py_RETURN_TRUE;
 	} else {
 		Py_RETURN_FALSE;
 	}
 };
 
+static PyObject *dirstatetuple_get_removed(dirstateTupleObject *self)
+{
+	if (self->state == 'r') {
+		Py_RETURN_TRUE;
+	} else {
+		Py_RETURN_FALSE;
+	}
+};
+
 static PyGetSetDef dirstatetuple_getset[] = {
     {"state", (getter)dirstatetuple_get_state, NULL, "state", NULL},
     {"merged", (getter)dirstatetuple_get_merged, NULL, "merged", NULL},
     {"from_p2", (getter)dirstatetuple_get_from_p2, NULL, "from_p2", NULL},
+    {"removed", (getter)dirstatetuple_get_removed, NULL, "removed", NULL},
     {NULL} /* Sentinel */
 };
 
 PyTypeObject dirstateTupleType = {
     PyVarObject_HEAD_INIT(NULL, 0)      /* header */
     "dirstate_tuple",                   /* tp_name */
     sizeof(dirstateTupleObject),        /* tp_basicsize */
     0,                                  /* tp_itemsize */
     (destructor)dirstate_tuple_dealloc, /* tp_dealloc */
     0,                                  /* tp_print */
     0,                                  /* tp_getattr */
     0,                                  /* tp_setattr */
     0,                                  /* tp_compare */
     0,                                  /* tp_repr */
     0,                                  /* tp_as_number */
     &dirstate_tuple_sq,                 /* tp_as_sequence */
     0,                                  /* tp_as_mapping */
     0,                                  /* tp_hash  */
     0,                                  /* tp_call */
     0,                                  /* tp_str */
     0,                                  /* tp_getattro */
     0,                                  /* tp_setattro */
     0,                                  /* tp_as_buffer */
     Py_TPFLAGS_DEFAULT,                 /* tp_flags */
     "dirstate tuple",                   /* tp_doc */
     0,                                  /* tp_traverse */
     0,                                  /* tp_clear */
     0,                                  /* tp_richcompare */
     0,                                  /* tp_weaklistoffset */
     0,                                  /* tp_iter */
     0,                                  /* tp_iternext */
     dirstatetuple_methods,              /* tp_methods */
     0,                                  /* tp_members */
     dirstatetuple_getset,               /* tp_getset */
     0,                                  /* tp_base */
     0,                                  /* tp_dict */
     0,                                  /* tp_descr_get */
     0,                                  /* tp_descr_set */
     0,                                  /* tp_dictoffset */
     0,                                  /* tp_init */
     0,                                  /* tp_alloc */
     dirstate_tuple_new,                 /* tp_new */
 };
 
 static PyObject *parse_dirstate(PyObject *self, PyObject *args)
 {
 	PyObject *dmap, *cmap, *parents = NULL, *ret = NULL;
 	PyObject *fname = NULL, *cname = NULL, *entry = NULL;
 	char state, *cur, *str, *cpos;
 	int mode, size, mtime;
 	unsigned int flen, pos = 40;
 	Py_ssize_t len = 40;
 	Py_ssize_t readlen;
 
 	if (!PyArg_ParseTuple(
 	        args, PY23("O!O!s#:parse_dirstate", "O!O!y#:parse_dirstate"),
 	        &PyDict_Type, &dmap, &PyDict_Type, &cmap, &str, &readlen)) {
 		goto quit;
 	}
 
 	len = readlen;
 
 	/* read parents */
 	if (len < 40) {
 		PyErr_SetString(PyExc_ValueError,
 		                "too little data for parents");
 		goto quit;
 	}
 
 	parents = Py_BuildValue(PY23("s#s#", "y#y#"), str, (Py_ssize_t)20,
 	                        str + 20, (Py_ssize_t)20);
 	if (!parents) {
 		goto quit;
 	}
 
 	/* read filenames */
 	while (pos >= 40 && pos < len) {
 		if (pos + 17 > len) {
 			PyErr_SetString(PyExc_ValueError,
 			                "overflow in dirstate");
 			goto quit;
 		}
 		cur = str + pos;
 		/* unpack header */
 		state = *cur;
 		mode = getbe32(cur + 1);
 		size = getbe32(cur + 5);
 		mtime = getbe32(cur + 9);
 		flen = getbe32(cur + 13);
 		pos += 17;
 		cur += 17;
 		if (flen > len - pos) {
 			PyErr_SetString(PyExc_ValueError,
 			                "overflow in dirstate");
 			goto quit;
 		}
 
 		entry =
 		    (PyObject *)make_dirstate_tuple(state, mode, size, mtime);
 		cpos = memchr(cur, 0, flen);
 		if (cpos) {
 			fname = PyBytes_FromStringAndSize(cur, cpos - cur);
 			cname = PyBytes_FromStringAndSize(
 			    cpos + 1, flen - (cpos - cur) - 1);
 			if (!fname || !cname ||
 			    PyDict_SetItem(cmap, fname, cname) == -1 ||
 			    PyDict_SetItem(dmap, fname, entry) == -1) {
 				goto quit;
 			}
 			Py_DECREF(cname);
 		} else {
 			fname = PyBytes_FromStringAndSize(cur, flen);
 			if (!fname ||
 			    PyDict_SetItem(dmap, fname, entry) == -1) {
 				goto quit;
 			}
 		}
 		Py_DECREF(fname);
 		Py_DECREF(entry);
 		fname = cname = entry = NULL;
 		pos += flen;
 	}
 
 	ret = parents;
 	Py_INCREF(ret);
 quit:
 	Py_XDECREF(fname);
 	Py_XDECREF(cname);
 	Py_XDECREF(entry);
 	Py_XDECREF(parents);
 	return ret;
 }
 
 /*
  * Build a set of non-normal and other parent entries from the dirstate dmap
  */
 static PyObject *nonnormalotherparententries(PyObject *self, PyObject *args)
 {
 	PyObject *dmap, *fname, *v;
 	PyObject *nonnset = NULL, *otherpset = NULL, *result = NULL;
 	Py_ssize_t pos;
 
 	if (!PyArg_ParseTuple(args, "O!:nonnormalentries", &PyDict_Type,
 	                      &dmap)) {
 		goto bail;
 	}
 
 	nonnset = PySet_New(NULL);
 	if (nonnset == NULL) {
 		goto bail;
 	}
 
 	otherpset = PySet_New(NULL);
 	if (otherpset == NULL) {
 		goto bail;
 	}
 
 	pos = 0;
 	while (PyDict_Next(dmap, &pos, &fname, &v)) {
 		dirstateTupleObject *t;
 		if (!dirstate_tuple_check(v)) {
 			PyErr_SetString(PyExc_TypeError,
 			                "expected a dirstate tuple");
 			goto bail;
 		}
 		t = (dirstateTupleObject *)v;
 
 		if (t->state == 'n' && t->size == -2) {
 			if (PySet_Add(otherpset, fname) == -1) {
 				goto bail;
 			}
 		}
 
 		if (t->state == 'n' && t->mtime != -1) {
 			continue;
 		}
 		if (PySet_Add(nonnset, fname) == -1) {
 			goto bail;
 		}
 	}
 
 	result = Py_BuildValue("(OO)", nonnset, otherpset);
 	if (result == NULL) {
 		goto bail;
 	}
 	Py_DECREF(nonnset);
 	Py_DECREF(otherpset);
 	return result;
 bail:
 	Py_XDECREF(nonnset);
 	Py_XDECREF(otherpset);
 	Py_XDECREF(result);
 	return NULL;
 }
 
 /*
  * Efficiently pack a dirstate object into its on-disk format.
  */
 static PyObject *pack_dirstate(PyObject *self, PyObject *args)
 {
 	PyObject *packobj = NULL;
 	PyObject *map, *copymap, *pl, *mtime_unset = NULL;
 	Py_ssize_t nbytes, pos, l;
 	PyObject *k, *v = NULL, *pn;
 	char *p, *s;
 	int now;
 
 	if (!PyArg_ParseTuple(args, "O!O!O!i:pack_dirstate", &PyDict_Type, &map,
 	                      &PyDict_Type, &copymap, &PyTuple_Type, &pl,
 	                      &now)) {
 		return NULL;
 	}
 
 	if (PyTuple_Size(pl) != 2) {
 		PyErr_SetString(PyExc_TypeError, "expected 2-element tuple");
 		return NULL;
 	}
 
 	/* Figure out how much we need to allocate. */
 	for (nbytes = 40, pos = 0; PyDict_Next(map, &pos, &k, &v);) {
 		PyObject *c;
 		if (!PyBytes_Check(k)) {
 			PyErr_SetString(PyExc_TypeError, "expected string key");
 			goto bail;
 		}
 		nbytes += PyBytes_GET_SIZE(k) + 17;
 		c = PyDict_GetItem(copymap, k);
 		if (c) {
 			if (!PyBytes_Check(c)) {
 				PyErr_SetString(PyExc_TypeError,
 				                "expected string key");
 				goto bail;
 			}
 			nbytes += PyBytes_GET_SIZE(c) + 1;
 		}
 	}
 
 	packobj = PyBytes_FromStringAndSize(NULL, nbytes);
 	if (packobj == NULL) {
 		goto bail;
 	}
 
 	p = PyBytes_AS_STRING(packobj);
 
 	pn = PyTuple_GET_ITEM(pl, 0);
 	if (PyBytes_AsStringAndSize(pn, &s, &l) == -1 || l != 20) {
 		PyErr_SetString(PyExc_TypeError, "expected a 20-byte hash");
 		goto bail;
 	}
 	memcpy(p, s, l);
 	p += 20;
 	pn = PyTuple_GET_ITEM(pl, 1);
 	if (PyBytes_AsStringAndSize(pn, &s, &l) == -1 || l != 20) {
 		PyErr_SetString(PyExc_TypeError, "expected a 20-byte hash");
 		goto bail;
 	}
 	memcpy(p, s, l);
 	p += 20;
 
 	for (pos = 0; PyDict_Next(map, &pos, &k, &v);) {
 		dirstateTupleObject *tuple;
 		char state;
 		int mode, size, mtime;
 		Py_ssize_t len, l;
 		PyObject *o;
 		char *t;
 
 		if (!dirstate_tuple_check(v)) {
 			PyErr_SetString(PyExc_TypeError,
 			                "expected a dirstate tuple");
 			goto bail;
 		}
 		tuple = (dirstateTupleObject *)v;
 
 		state = tuple->state;
 		mode = tuple->mode;
 		size = tuple->size;
 		mtime = tuple->mtime;
 		if (state == 'n' && mtime == now) {
 			/* See pure/parsers.py:pack_dirstate for why we do
 			 * this. */
 			mtime = -1;
 			mtime_unset = (PyObject *)make_dirstate_tuple(
 			    state, mode, size, mtime);
 			if (!mtime_unset) {
 				goto bail;
 			}
 			if (PyDict_SetItem(map, k, mtime_unset) == -1) {
 				goto bail;
 			}
 			Py_DECREF(mtime_unset);
 			mtime_unset = NULL;
 		}
 		*p++ = state;
 		putbe32((uint32_t)mode, p);
 		putbe32((uint32_t)size, p + 4);
 		putbe32((uint32_t)mtime, p + 8);
 		t = p + 12;
 		p += 16;
 		len = PyBytes_GET_SIZE(k);
 		memcpy(p, PyBytes_AS_STRING(k), len);
 		p += len;
 		o = PyDict_GetItem(copymap, k);
 		if (o) {
 			*p++ = '\0';
 			l = PyBytes_GET_SIZE(o);
 			memcpy(p, PyBytes_AS_STRING(o), l);
 			p += l;
 			len += l + 1;
 		}
 		putbe32((uint32_t)len, t);
 	}
 
 	pos = p - PyBytes_AS_STRING(packobj);
 	if (pos != nbytes) {
 		PyErr_Format(PyExc_SystemError, "bad dirstate size: %ld != %ld",
 		             (long)pos, (long)nbytes);
 		goto bail;
 	}
 
 	return packobj;
 bail:
 	Py_XDECREF(mtime_unset);
 	Py_XDECREF(packobj);
 	Py_XDECREF(v);
 	return NULL;
 }
 
 #define BUMPED_FIX 1
 #define USING_SHA_256 2
 #define FM1_HEADER_SIZE (4 + 8 + 2 + 2 + 1 + 1 + 1)
 
 static PyObject *readshas(const char *source, unsigned char num,
                           Py_ssize_t hashwidth)
 {
 	int i;
 	PyObject *list = PyTuple_New(num);
 	if (list == NULL) {
 		return NULL;
 	}
 	for (i = 0; i < num; i++) {
 		PyObject *hash = PyBytes_FromStringAndSize(source, hashwidth);
 		if (hash == NULL) {
 			Py_DECREF(list);
 			return NULL;
 		}
 		PyTuple_SET_ITEM(list, i, hash);
 		source += hashwidth;
 	}
 	return list;
 }
 
 static PyObject *fm1readmarker(const char *databegin, const char *dataend,
                                uint32_t *msize)
 {
 	const char *data = databegin;
 	const char *meta;
 
 	double mtime;
 	int16_t tz;
 	uint16_t flags;
 	unsigned char nsuccs, nparents, nmetadata;
 	Py_ssize_t hashwidth = 20;
 
 	PyObject *prec = NULL, *parents = NULL, *succs = NULL;
 	PyObject *metadata = NULL, *ret = NULL;
 	int i;
 
 	if (data + FM1_HEADER_SIZE > dataend) {
 		goto overflow;
 	}
 
 	*msize = getbe32(data);
 	data += 4;
 	mtime = getbefloat64(data);
 	data += 8;
 	tz = getbeint16(data);
 	data += 2;
 	flags = getbeuint16(data);
 	data += 2;
 
 	if (flags & USING_SHA_256) {
 		hashwidth = 32;
 	}
 
 	nsuccs = (unsigned char)(*data++);
 	nparents = (unsigned char)(*data++);
 	nmetadata = (unsigned char)(*data++);
 
 	if (databegin + *msize > dataend) {
 		goto overflow;
 	}
 	dataend = databegin + *msize; /* narrow down to marker size */
 
 	if (data + hashwidth > dataend) {
 		goto overflow;
 	}
 	prec = PyBytes_FromStringAndSize(data, hashwidth);
 	data += hashwidth;
 	if (prec == NULL) {
 		goto bail;
 	}
 
 	if (data + nsuccs * hashwidth > dataend) {
 		goto overflow;
 	}
 	succs = readshas(data, nsuccs, hashwidth);
 	if (succs == NULL) {
 		goto bail;
 	}
 	data += nsuccs * hashwidth;
 
 	if (nparents == 1 || nparents == 2) {
 		if (data + nparents * hashwidth > dataend) {
 			goto overflow;
 		}
 		parents = readshas(data, nparents, hashwidth);
 		if (parents == NULL) {
 			goto bail;
 		}
 		data += nparents * hashwidth;
 	} else {
 		parents = Py_None;
 		Py_INCREF(parents);
 	}
 
 	if (data + 2 * nmetadata > dataend) {
 		goto overflow;
 	}
 	meta = data + (2 * nmetadata);
 	metadata = PyTuple_New(nmetadata);
 	if (metadata == NULL) {
 		goto bail;
 	}
 	for (i = 0; i < nmetadata; i++) {
 		PyObject *tmp, *left = NULL, *right = NULL;
 		Py_ssize_t leftsize = (unsigned char)(*data++);
 		Py_ssize_t rightsize = (unsigned char)(*data++);
 		if (meta + leftsize + rightsize > dataend) {
 			goto overflow;
 		}
 		left = PyBytes_FromStringAndSize(meta, leftsize);
 		meta += leftsize;
 		right = PyBytes_FromStringAndSize(meta, rightsize);
 		meta += rightsize;
 		tmp = PyTuple_New(2);
 		if (!left || !right || !tmp) {
 			Py_XDECREF(left);
 			Py_XDECREF(right);
 			Py_XDECREF(tmp);
 			goto bail;
 		}
 		PyTuple_SET_ITEM(tmp, 0, left);
 		PyTuple_SET_ITEM(tmp, 1, right);
 		PyTuple_SET_ITEM(metadata, i, tmp);
 	}
 	ret = Py_BuildValue("(OOHO(di)O)", prec, succs, flags, metadata, mtime,
 	                    (int)tz * 60, parents);
 	goto bail; /* return successfully */
 
 overflow:
 	PyErr_SetString(PyExc_ValueError, "overflow in obsstore");
 bail:
 	Py_XDECREF(prec);
 	Py_XDECREF(succs);
 	Py_XDECREF(metadata);
 	Py_XDECREF(parents);
 	return ret;
 }
 
 static PyObject *fm1readmarkers(PyObject *self, PyObject *args)
 {
 	const char *data, *dataend;
 	Py_ssize_t datalen, offset, stop;
 	PyObject *markers = NULL;
 
 	if (!PyArg_ParseTuple(args, PY23("s#nn", "y#nn"), &data, &datalen,
 	                      &offset, &stop)) {
 		return NULL;
 	}
 	if (offset < 0) {
 		PyErr_SetString(PyExc_ValueError,
 		                "invalid negative offset in fm1readmarkers");
 		return NULL;
 	}
 	if (stop > datalen) {
 		PyErr_SetString(
 		    PyExc_ValueError,
 		    "stop longer than data length in fm1readmarkers");
 		return NULL;
 	}
 	dataend = data + datalen;
 	data += offset;
 	markers = PyList_New(0);
 	if (!markers) {
 		return NULL;
 	}
 	while (offset < stop) {
 		uint32_t msize;
 		int error;
 		PyObject *record = fm1readmarker(data, dataend, &msize);
 		if (!record) {
 			goto bail;
 		}
 		error = PyList_Append(markers, record);
 		Py_DECREF(record);
 		if (error) {
 			goto bail;
 		}
 		data += msize;
 		offset += msize;
 	}
 	return markers;
 bail:
 	Py_DECREF(markers);
 	return NULL;
 }
 
 static char parsers_doc[] = "Efficient content parsing.";
 
 PyObject *encodedir(PyObject *self, PyObject *args);
 PyObject *pathencode(PyObject *self, PyObject *args);
 PyObject *lowerencode(PyObject *self, PyObject *args);
 PyObject *parse_index2(PyObject *self, PyObject *args, PyObject *kwargs);
 
 static PyMethodDef methods[] = {
     {"pack_dirstate", pack_dirstate, METH_VARARGS, "pack a dirstate\n"},
     {"nonnormalotherparententries", nonnormalotherparententries, METH_VARARGS,
      "create a set containing non-normal and other parent entries of given "
      "dirstate\n"},
     {"parse_dirstate", parse_dirstate, METH_VARARGS, "parse a dirstate\n"},
     {"parse_index2", (PyCFunction)parse_index2, METH_VARARGS | METH_KEYWORDS,
      "parse a revlog index\n"},
     {"isasciistr", isasciistr, METH_VARARGS, "check if an ASCII string\n"},
     {"asciilower", asciilower, METH_VARARGS, "lowercase an ASCII string\n"},
     {"asciiupper", asciiupper, METH_VARARGS, "uppercase an ASCII string\n"},
     {"dict_new_presized", dict_new_presized, METH_VARARGS,
      "construct a dict with an expected size\n"},
     {"make_file_foldmap", make_file_foldmap, METH_VARARGS,
      "make file foldmap\n"},
     {"jsonescapeu8fast", jsonescapeu8fast, METH_VARARGS,
      "escape a UTF-8 byte string to JSON (fast path)\n"},
     {"encodedir", encodedir, METH_VARARGS, "encodedir a path\n"},
     {"pathencode", pathencode, METH_VARARGS, "fncache-encode a path\n"},
     {"lowerencode", lowerencode, METH_VARARGS, "lower-encode a path\n"},
     {"fm1readmarkers", fm1readmarkers, METH_VARARGS,
      "parse v1 obsolete markers\n"},
     {NULL, NULL}};
 
 void dirs_module_init(PyObject *mod);
 void manifest_module_init(PyObject *mod);
 void revlog_module_init(PyObject *mod);
 
 static const int version = 20;
 
 static void module_init(PyObject *mod)
 {
 	PyObject *capsule = NULL;
 	PyModule_AddIntConstant(mod, "version", version);
 
 	/* This module constant has two purposes.  First, it lets us unit test
 	 * the ImportError raised without hard-coding any error text.  This
 	 * means we can change the text in the future without breaking tests,
 	 * even across changesets without a recompile.  Second, its presence
 	 * can be used to determine whether the version-checking logic is
 	 * present, which also helps in testing across changesets without a
 	 * recompile.  Note that this means the pure-Python version of parsers
 	 * should not have this module constant. */
 	PyModule_AddStringConstant(mod, "versionerrortext", versionerrortext);
 
 	dirs_module_init(mod);
 	manifest_module_init(mod);
 	revlog_module_init(mod);
 
 	capsule = PyCapsule_New(
 	    make_dirstate_tuple,
 	    "mercurial.cext.parsers.make_dirstate_tuple_CAPI", NULL);
 	if (capsule != NULL)
 		PyModule_AddObject(mod, "make_dirstate_tuple_CAPI", capsule);
 
 	if (PyType_Ready(&dirstateTupleType) < 0) {
 		return;
 	}
 	Py_INCREF(&dirstateTupleType);
 	PyModule_AddObject(mod, "dirstatetuple",
 	                   (PyObject *)&dirstateTupleType);
 }
 
 static int check_python_version(void)
 {
 	PyObject *sys = PyImport_ImportModule("sys"), *ver;
 	long hexversion;
 	if (!sys) {
 		return -1;
 	}
 	ver = PyObject_GetAttrString(sys, "hexversion");
 	Py_DECREF(sys);
 	if (!ver) {
 		return -1;
 	}
 	hexversion = PyInt_AsLong(ver);
 	Py_DECREF(ver);
 	/* sys.hexversion is a 32-bit number by default, so the -1 case
 	 * should only occur in unusual circumstances (e.g. if sys.hexversion
 	 * is manually set to an invalid value). */
 	if ((hexversion == -1) || (hexversion >> 16 != PY_VERSION_HEX >> 16)) {
 		PyErr_Format(PyExc_ImportError,
 		             "%s: The Mercurial extension "
 		             "modules were compiled with Python " PY_VERSION
 		             ", but "
 		             "Mercurial is currently using Python with "
 		             "sys.hexversion=%ld: "
 		             "Python %s\n at: %s",
 		             versionerrortext, hexversion, Py_GetVersion(),
 		             Py_GetProgramFullPath());
 		return -1;
 	}
 	return 0;
 }
 
 #ifdef IS_PY3K
 static struct PyModuleDef parsers_module = {PyModuleDef_HEAD_INIT, "parsers",
                                             parsers_doc, -1, methods};
 
 PyMODINIT_FUNC PyInit_parsers(void)
 {
 	PyObject *mod;
 
 	if (check_python_version() == -1)
 		return NULL;
 	mod = PyModule_Create(&parsers_module);
 	module_init(mod);
 	return mod;
 }
 #else
 PyMODINIT_FUNC initparsers(void)
 {
 	PyObject *mod;
 
 	if (check_python_version() == -1) {
 		return;
 	}
 	mod = Py_InitModule3("parsers", methods, parsers_doc);
 	module_init(mod);
 }
 #endif

mercurial/dirstate.py

@@ -1,1453 +1,1451
 # dirstate.py - working directory tracking for mercurial
 #
 # Copyright 2005-2007 Olivia Mackall <[e-mail]>
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from __future__ import absolute_import
 
 import collections
 import contextlib
 import errno
 import os
 import stat
 
 from .i18n import _
 from .pycompat import delattr
 
 from hgdemandimport import tracing
 
 from . import (
     dirstatemap,
     encoding,
     error,
     match as matchmod,
     pathutil,
     policy,
     pycompat,
     scmutil,
     sparse,
     util,
 )
 
 from .interfaces import (
     dirstate as intdirstate,
     util as interfaceutil,
 )
 
 parsers = policy.importmod('parsers')
 rustmod = policy.importrust('dirstate')
 
 SUPPORTS_DIRSTATE_V2 = rustmod is not None
 
 propertycache = util.propertycache
 filecache = scmutil.filecache
 _rangemask = 0x7FFFFFFF
 
 dirstatetuple = parsers.dirstatetuple
 
 
 # a special value used internally for `size` if the file come from the other parent
 FROM_P2 = dirstatemap.FROM_P2
 
 # a special value used internally for `size` if the file is modified/merged/added
 NONNORMAL = dirstatemap.NONNORMAL
 
 # a special value used internally for `time` if the time is ambigeous
 AMBIGUOUS_TIME = dirstatemap.AMBIGUOUS_TIME
 
 
 class repocache(filecache):
     """filecache for files in .hg/"""
 
     def join(self, obj, fname):
         return obj._opener.join(fname)
 
 
 class rootcache(filecache):
     """filecache for files in the repository root"""
 
     def join(self, obj, fname):
         return obj._join(fname)
 
 
 def _getfsnow(vfs):
     '''Get "now" timestamp on filesystem'''
     tmpfd, tmpname = vfs.mkstemp()
     try:
         return os.fstat(tmpfd)[stat.ST_MTIME]
     finally:
         os.close(tmpfd)
         vfs.unlink(tmpname)
 
 
 @interfaceutil.implementer(intdirstate.idirstate)
 class dirstate(object):
     def __init__(
         self,
         opener,
         ui,
         root,
         validate,
         sparsematchfn,
         nodeconstants,
         use_dirstate_v2,
     ):
         """Create a new dirstate object.
 
         opener is an open()-like callable that can be used to open the
         dirstate file; root is the root of the directory tracked by
         the dirstate.
         """
         self._use_dirstate_v2 = use_dirstate_v2
         self._nodeconstants = nodeconstants
         self._opener = opener
         self._validate = validate
         self._root = root
         self._sparsematchfn = sparsematchfn
         # ntpath.join(root, '') of Python 2.7.9 does not add sep if root is
         # UNC path pointing to root share (issue4557)
         self._rootdir = pathutil.normasprefix(root)
         self._dirty = False
         self._lastnormaltime = 0
         self._ui = ui
         self._filecache = {}
         self._parentwriters = 0
         self._filename = b'dirstate'
         self._pendingfilename = b'%s.pending' % self._filename
         self._plchangecallbacks = {}
         self._origpl = None
         self._updatedfiles = set()
         self._mapcls = dirstatemap.dirstatemap
         # Access and cache cwd early, so we don't access it for the first time
         # after a working-copy update caused it to not exist (accessing it then
         # raises an exception).
         self._cwd
 
     def prefetch_parents(self):
         """make sure the parents are loaded
 
         Used to avoid a race condition.
         """
         self._pl
 
     @contextlib.contextmanager
     def parentchange(self):
         """Context manager for handling dirstate parents.
 
         If an exception occurs in the scope of the context manager,
         the incoherent dirstate won't be written when wlock is
         released.
         """
         self._parentwriters += 1
         yield
         # Typically we want the "undo" step of a context manager in a
         # finally block so it happens even when an exception
         # occurs. In this case, however, we only want to decrement
         # parentwriters if the code in the with statement exits
         # normally, so we don't have a try/finally here on purpose.
         self._parentwriters -= 1
 
     def pendingparentchange(self):
         """Returns true if the dirstate is in the middle of a set of changes
         that modify the dirstate parent.
         """
         return self._parentwriters > 0
 
     @propertycache
     def _map(self):
         """Return the dirstate contents (see documentation for dirstatemap)."""
         self._map = self._mapcls(
             self._ui,
             self._opener,
             self._root,
             self._nodeconstants,
             self._use_dirstate_v2,
         )
         return self._map
 
     @property
     def _sparsematcher(self):
         """The matcher for the sparse checkout.
 
         The working directory may not include every file from a manifest. The
         matcher obtained by this property will match a path if it is to be
         included in the working directory.
         """
         # TODO there is potential to cache this property. For now, the matcher
         # is resolved on every access. (But the called function does use a
         # cache to keep the lookup fast.)
         return self._sparsematchfn()
 
     @repocache(b'branch')
     def _branch(self):
         try:
             return self._opener.read(b"branch").strip() or b"default"
         except IOError as inst:
             if inst.errno != errno.ENOENT:
                 raise
             return b"default"
 
     @property
     def _pl(self):
         return self._map.parents()
 
     def hasdir(self, d):
         return self._map.hastrackeddir(d)
 
     @rootcache(b'.hgignore')
     def _ignore(self):
         files = self._ignorefiles()
         if not files:
             return matchmod.never()
 
         pats = [b'include:%s' % f for f in files]
         return matchmod.match(self._root, b'', [], pats, warn=self._ui.warn)
 
     @propertycache
     def _slash(self):
         return self._ui.configbool(b'ui', b'slash') and pycompat.ossep != b'/'
 
     @propertycache
     def _checklink(self):
         return util.checklink(self._root)
 
     @propertycache
     def _checkexec(self):
         return bool(util.checkexec(self._root))
 
     @propertycache
     def _checkcase(self):
         return not util.fscasesensitive(self._join(b'.hg'))
 
     def _join(self, f):
         # much faster than os.path.join()
         # it's safe because f is always a relative path
         return self._rootdir + f
 
     def flagfunc(self, buildfallback):
         if self._checklink and self._checkexec:
 
             def f(x):
                 try:
                     st = os.lstat(self._join(x))
                     if util.statislink(st):
                         return b'l'
                     if util.statisexec(st):
                         return b'x'
                 except OSError:
                     pass
                 return b''
 
             return f
 
         fallback = buildfallback()
         if self._checklink:
 
             def f(x):
                 if os.path.islink(self._join(x)):
                     return b'l'
                 if b'x' in fallback(x):
                     return b'x'
                 return b''
 
             return f
         if self._checkexec:
 
             def f(x):
                 if b'l' in fallback(x):
                     return b'l'
                 if util.isexec(self._join(x)):
                     return b'x'
                 return b''
 
             return f
         else:
             return fallback
 
     @propertycache
     def _cwd(self):
         # internal config: ui.forcecwd
         forcecwd = self._ui.config(b'ui', b'forcecwd')
         if forcecwd:
             return forcecwd
         return encoding.getcwd()
 
     def getcwd(self):
         """Return the path from which a canonical path is calculated.
 
         This path should be used to resolve file patterns or to convert
         canonical paths back to file paths for display. It shouldn't be
         used to get real file paths. Use vfs functions instead.
         """
         cwd = self._cwd
         if cwd == self._root:
             return b''
         # self._root ends with a path separator if self._root is '/' or 'C:\'
         rootsep = self._root
         if not util.endswithsep(rootsep):
             rootsep += pycompat.ossep
         if cwd.startswith(rootsep):
             return cwd[len(rootsep) :]
         else:
             # we're outside the repo. return an absolute path.
             return cwd
 
     def pathto(self, f, cwd=None):
         if cwd is None:
             cwd = self.getcwd()
         path = util.pathto(self._root, cwd, f)
         if self._slash:
             return util.pconvert(path)
         return path
 
     def __getitem__(self, key):
         """Return the current state of key (a filename) in the dirstate.
 
         States are:
           n  normal
           m  needs merging
           r  marked for removal
           a  marked for addition
           ?  not tracked
 
         XXX The "state" is a bit obscure to be in the "public" API. we should
         consider migrating all user of this to going through the dirstate entry
         instead.
         """
         entry = self._map.get(key)
         if entry is not None:
             return entry.state
         return b'?'
 
     def __contains__(self, key):
         return key in self._map
 
     def __iter__(self):
         return iter(sorted(self._map))
 
     def items(self):
         return pycompat.iteritems(self._map)
 
     iteritems = items
 
     def directories(self):
         return self._map.directories()
 
     def parents(self):
         return [self._validate(p) for p in self._pl]
 
     def p1(self):
         return self._validate(self._pl[0])
 
     def p2(self):
         return self._validate(self._pl[1])
 
     @property
     def in_merge(self):
         """True if a merge is in progress"""
         return self._pl[1] != self._nodeconstants.nullid
 
     def branch(self):
         return encoding.tolocal(self._branch)
 
     def setparents(self, p1, p2=None):
         """Set dirstate parents to p1 and p2.
 
         When moving from two parents to one, "merged" entries a
         adjusted to normal and previous copy records discarded and
         returned by the call.
 
         See localrepo.setparents()
         """
         if p2 is None:
             p2 = self._nodeconstants.nullid
         if self._parentwriters == 0:
             raise ValueError(
                 b"cannot set dirstate parent outside of "
                 b"dirstate.parentchange context manager"
             )
 
         self._dirty = True
         oldp2 = self._pl[1]
         if self._origpl is None:
             self._origpl = self._pl
         self._map.setparents(p1, p2)
         copies = {}
         if (
             oldp2 != self._nodeconstants.nullid
             and p2 == self._nodeconstants.nullid
         ):
             candidatefiles = self._map.non_normal_or_other_parent_paths()
 
             for f in candidatefiles:
                 s = self._map.get(f)
                 if s is None:
                     continue
 
                 # Discard "merged" markers when moving away from a merge state
                 if s.merged:
                     source = self._map.copymap.get(f)
                     if source:
                         copies[f] = source
                     self.normallookup(f)
                 # Also fix up otherparent markers
                 elif s.state == b'n' and s.from_p2:
                     source = self._map.copymap.get(f)
                     if source:
                         copies[f] = source
                     self.add(f)
         return copies
 
     def setbranch(self, branch):
         self.__class__._branch.set(self, encoding.fromlocal(branch))
         f = self._opener(b'branch', b'w', atomictemp=True, checkambig=True)
         try:
             f.write(self._branch + b'\n')
             f.close()
 
             # make sure filecache has the correct stat info for _branch after
             # replacing the underlying file
             ce = self._filecache[b'_branch']
             if ce:
                 ce.refresh()
         except:  # re-raises
             f.discard()
             raise
 
     def invalidate(self):
         """Causes the next access to reread the dirstate.
 
         This is different from localrepo.invalidatedirstate() because it always
         rereads the dirstate. Use localrepo.invalidatedirstate() if you want to
         check whether the dirstate has changed before rereading it."""
 
         for a in ("_map", "_branch", "_ignore"):
             if a in self.__dict__:
                 delattr(self, a)
         self._lastnormaltime = 0
         self._dirty = False
         self._updatedfiles.clear()
         self._parentwriters = 0
         self._origpl = None
 
     def copy(self, source, dest):
         """Mark dest as a copy of source. Unmark dest if source is None."""
         if source == dest:
             return
         self._dirty = True
         if source is not None:
             self._map.copymap[dest] = source
             self._updatedfiles.add(source)
             self._updatedfiles.add(dest)
         elif self._map.copymap.pop(dest, None):
             self._updatedfiles.add(dest)
 
     def copied(self, file):
         return self._map.copymap.get(file, None)
 
     def copies(self):
         return self._map.copymap
 
     def _addpath(
         self,
         f,
         state,
         mode,
         size=NONNORMAL,
         mtime=AMBIGUOUS_TIME,
         from_p2=False,
         possibly_dirty=False,
     ):
         oldstate = self[f]
         if state == b'a' or oldstate == b'r':
             scmutil.checkfilename(f)
             if self._map.hastrackeddir(f):
                 msg = _(b'directory %r already in dirstate')
                 msg %= pycompat.bytestr(f)
                 raise error.Abort(msg)
             # shadows
             for d in pathutil.finddirs(f):
                 if self._map.hastrackeddir(d):
                     break
                 entry = self._map.get(d)
-                if entry is not None and entry.state != b'r':
+                if entry is not None and not entry.removed:
                     msg = _(b'file %r in dirstate clashes with %r')
                     msg %= (pycompat.bytestr(d), pycompat.bytestr(f))
                     raise error.Abort(msg)
         if state == b'a':
             assert not possibly_dirty
             assert not from_p2
             size = NONNORMAL
             mtime = AMBIGUOUS_TIME
         elif from_p2:
             assert not possibly_dirty
             size = FROM_P2
             mtime = AMBIGUOUS_TIME
         elif possibly_dirty:
             mtime = AMBIGUOUS_TIME
         else:
             assert size != FROM_P2
             assert size != NONNORMAL
             size = size & _rangemask
             mtime = mtime & _rangemask
         self._dirty = True
         self._updatedfiles.add(f)
         self._map.addfile(f, oldstate, state, mode, size, mtime)
 
     def normal(self, f, parentfiledata=None):
         """Mark a file normal and clean.
 
         parentfiledata: (mode, size, mtime) of the clean file
 
         parentfiledata should be computed from memory (for mode,
         size), as or close as possible from the point where we
         determined the file was clean, to limit the risk of the
         file having been changed by an external process between the
         moment where the file was determined to be clean and now."""
         if parentfiledata:
             (mode, size, mtime) = parentfiledata
         else:
             s = os.lstat(self._join(f))
             mode = s.st_mode
             size = s.st_size
             mtime = s[stat.ST_MTIME]
         self._addpath(f, b'n', mode, size, mtime)
         self._map.copymap.pop(f, None)
         if f in self._map.nonnormalset:
             self._map.nonnormalset.remove(f)
         if mtime > self._lastnormaltime:
             # Remember the most recent modification timeslot for status(),
             # to make sure we won't miss future size-preserving file content
             # modifications that happen within the same timeslot.
             self._lastnormaltime = mtime
 
     def normallookup(self, f):
         '''Mark a file normal, but possibly dirty.'''
         if self.in_merge:
             # if there is a merge going on and the file was either
             # "merged" or coming from other parent (-2) before
             # being removed, restore that state.
             entry = self._map.get(f)
             if entry is not None:
-                if entry.state == b'r' and (
-                    entry[2] == NONNORMAL or entry.from_p2
-                ):
+                if entry.removed and (entry[2] == NONNORMAL or entry.from_p2):
                     source = self._map.copymap.get(f)
                     if entry[2] == NONNORMAL:
                         self.merge(f)
                     elif entry.from_p2:
                         self.otherparent(f)
                     if source:
                         self.copy(source, f)
                     return
                 if entry.merged or entry.state == b'n' and entry.from_p2:
                     return
         self._addpath(f, b'n', 0, possibly_dirty=True)
         self._map.copymap.pop(f, None)
 
     def otherparent(self, f):
         '''Mark as coming from the other parent, always dirty.'''
         if not self.in_merge:
             msg = _(b"setting %r to other parent only allowed in merges") % f
             raise error.Abort(msg)
         if f in self and self[f] == b'n':
             # merge-like
             self._addpath(f, b'm', 0, from_p2=True)
         else:
             # add-like
             self._addpath(f, b'n', 0, from_p2=True)
         self._map.copymap.pop(f, None)
 
     def add(self, f):
         '''Mark a file added.'''
         self._addpath(f, b'a', 0)
         self._map.copymap.pop(f, None)
 
     def remove(self, f):
         '''Mark a file removed.'''
         self._dirty = True
         self._updatedfiles.add(f)
         self._map.removefile(f, in_merge=self.in_merge)
 
     def merge(self, f):
         '''Mark a file merged.'''
         if not self.in_merge:
             return self.normallookup(f)
         return self.otherparent(f)
 
     def drop(self, f):
         '''Drop a file from the dirstate'''
         oldstate = self[f]
         if self._map.dropfile(f, oldstate):
             self._dirty = True
             self._updatedfiles.add(f)
             self._map.copymap.pop(f, None)
 
     def _discoverpath(self, path, normed, ignoremissing, exists, storemap):
         if exists is None:
             exists = os.path.lexists(os.path.join(self._root, path))
         if not exists:
             # Maybe a path component exists
             if not ignoremissing and b'/' in path:
                 d, f = path.rsplit(b'/', 1)
                 d = self._normalize(d, False, ignoremissing, None)
                 folded = d + b"/" + f
             else:
                 # No path components, preserve original case
                 folded = path
         else:
             # recursively normalize leading directory components
             # against dirstate
             if b'/' in normed:
                 d, f = normed.rsplit(b'/', 1)
                 d = self._normalize(d, False, ignoremissing, True)
                 r = self._root + b"/" + d
                 folded = d + b"/" + util.fspath(f, r)
             else:
                 folded = util.fspath(normed, self._root)
             storemap[normed] = folded
 
         return folded
 
     def _normalizefile(self, path, isknown, ignoremissing=False, exists=None):
         normed = util.normcase(path)
         folded = self._map.filefoldmap.get(normed, None)
         if folded is None:
             if isknown:
                 folded = path
             else:
                 folded = self._discoverpath(
                     path, normed, ignoremissing, exists, self._map.filefoldmap
                 )
         return folded
 
     def _normalize(self, path, isknown, ignoremissing=False, exists=None):
         normed = util.normcase(path)
         folded = self._map.filefoldmap.get(normed, None)
         if folded is None:
             folded = self._map.dirfoldmap.get(normed, None)
         if folded is None:
             if isknown:
                 folded = path
             else:
                 # store discovered result in dirfoldmap so that future
                 # normalizefile calls don't start matching directories
                 folded = self._discoverpath(
                     path, normed, ignoremissing, exists, self._map.dirfoldmap
                 )
         return folded
 
     def normalize(self, path, isknown=False, ignoremissing=False):
         """
         normalize the case of a pathname when on a casefolding filesystem
 
         isknown specifies whether the filename came from walking the
         disk, to avoid extra filesystem access.
 
         If ignoremissing is True, missing path are returned
         unchanged. Otherwise, we try harder to normalize possibly
         existing path components.
 
         The normalized case is determined based on the following precedence:
 
         - version of name already stored in the dirstate
         - version of name stored on disk
         - version provided via command arguments
         """
 
         if self._checkcase:
             return self._normalize(path, isknown, ignoremissing)
         return path
 
     def clear(self):
         self._map.clear()
         self._lastnormaltime = 0
         self._updatedfiles.clear()
         self._dirty = True
 
     def rebuild(self, parent, allfiles, changedfiles=None):
         if changedfiles is None:
             # Rebuild entire dirstate
             to_lookup = allfiles
             to_drop = []
             lastnormaltime = self._lastnormaltime
             self.clear()
             self._lastnormaltime = lastnormaltime
         elif len(changedfiles) < 10:
             # Avoid turning allfiles into a set, which can be expensive if it's
             # large.
             to_lookup = []
             to_drop = []
             for f in changedfiles:
                 if f in allfiles:
                     to_lookup.append(f)
                 else:
                     to_drop.append(f)
         else:
             changedfilesset = set(changedfiles)
             to_lookup = changedfilesset & set(allfiles)
             to_drop = changedfilesset - to_lookup
 
         if self._origpl is None:
             self._origpl = self._pl
         self._map.setparents(parent, self._nodeconstants.nullid)
 
         for f in to_lookup:
             self.normallookup(f)
         for f in to_drop:
             self.drop(f)
 
         self._dirty = True
 
     def identity(self):
         """Return identity of dirstate itself to detect changing in storage
 
         If identity of previous dirstate is equal to this, writing
         changes based on the former dirstate out can keep consistency.
         """
         return self._map.identity
 
     def write(self, tr):
         if not self._dirty:
             return
 
         filename = self._filename
         if tr:
             # 'dirstate.write()' is not only for writing in-memory
             # changes out, but also for dropping ambiguous timestamp.
             # delayed writing re-raise "ambiguous timestamp issue".
             # See also the wiki page below for detail:
             # https://www.mercurial-scm.org/wiki/DirstateTransactionPlan
 
             # emulate dropping timestamp in 'parsers.pack_dirstate'
             now = _getfsnow(self._opener)
             self._map.clearambiguoustimes(self._updatedfiles, now)
 
             # emulate that all 'dirstate.normal' results are written out
             self._lastnormaltime = 0
             self._updatedfiles.clear()
 
             # delay writing in-memory changes out
             tr.addfilegenerator(
                 b'dirstate',
                 (self._filename,),
                 self._writedirstate,
                 location=b'plain',
             )
             return
 
         st = self._opener(filename, b"w", atomictemp=True, checkambig=True)
         self._writedirstate(st)
 
     def addparentchangecallback(self, category, callback):
         """add a callback to be called when the wd parents are changed
 
         Callback will be called with the following arguments:
             dirstate, (oldp1, oldp2), (newp1, newp2)
 
         Category is a unique identifier to allow overwriting an old callback
         with a newer callback.
         """
         self._plchangecallbacks[category] = callback
 
     def _writedirstate(self, st):
         # notify callbacks about parents change
         if self._origpl is not None and self._origpl != self._pl:
             for c, callback in sorted(
                 pycompat.iteritems(self._plchangecallbacks)
             ):
                 callback(self, self._origpl, self._pl)
             self._origpl = None
         # use the modification time of the newly created temporary file as the
         # filesystem's notion of 'now'
         now = util.fstat(st)[stat.ST_MTIME] & _rangemask
 
         # enough 'delaywrite' prevents 'pack_dirstate' from dropping
         # timestamp of each entries in dirstate, because of 'now > mtime'
         delaywrite = self._ui.configint(b'debug', b'dirstate.delaywrite')
         if delaywrite > 0:
             # do we have any files to delay for?
             for f, e in pycompat.iteritems(self._map):
                 if e.state == b'n' and e[3] == now:
                     import time  # to avoid useless import
 
                     # rather than sleep n seconds, sleep until the next
                     # multiple of n seconds
                     clock = time.time()
                     start = int(clock) - (int(clock) % delaywrite)
                     end = start + delaywrite
                     time.sleep(end - clock)
                     now = end  # trust our estimate that the end is near now
                     break
 
         self._map.write(st, now)
         self._lastnormaltime = 0
         self._dirty = False
 
     def _dirignore(self, f):
         if self._ignore(f):
             return True
         for p in pathutil.finddirs(f):
             if self._ignore(p):
                 return True
         return False
 
     def _ignorefiles(self):
         files = []
         if os.path.exists(self._join(b'.hgignore')):
             files.append(self._join(b'.hgignore'))
         for name, path in self._ui.configitems(b"ui"):
             if name == b'ignore' or name.startswith(b'ignore.'):
                 # we need to use os.path.join here rather than self._join
                 # because path is arbitrary and user-specified
                 files.append(os.path.join(self._rootdir, util.expandpath(path)))
         return files
 
     def _ignorefileandline(self, f):
         files = collections.deque(self._ignorefiles())
         visited = set()
         while files:
             i = files.popleft()
             patterns = matchmod.readpatternfile(
                 i, self._ui.warn, sourceinfo=True
             )
             for pattern, lineno, line in patterns:
                 kind, p = matchmod._patsplit(pattern, b'glob')
                 if kind == b"subinclude":
                     if p not in visited:
                         files.append(p)
                     continue
                 m = matchmod.match(
                     self._root, b'', [], [pattern], warn=self._ui.warn
                 )
                 if m(f):
                     return (i, lineno, line)
             visited.add(i)
         return (None, -1, b"")
 
     def _walkexplicit(self, match, subrepos):
         """Get stat data about the files explicitly specified by match.
 
         Return a triple (results, dirsfound, dirsnotfound).
         - results is a mapping from filename to stat result. It also contains
           listings mapping subrepos and .hg to None.
         - dirsfound is a list of files found to be directories.
         - dirsnotfound is a list of files that the dirstate thinks are
           directories and that were not found."""
 
         def badtype(mode):
             kind = _(b'unknown')
             if stat.S_ISCHR(mode):
                 kind = _(b'character device')
             elif stat.S_ISBLK(mode):
                 kind = _(b'block device')
             elif stat.S_ISFIFO(mode):
                 kind = _(b'fifo')
             elif stat.S_ISSOCK(mode):
                 kind = _(b'socket')
             elif stat.S_ISDIR(mode):
                 kind = _(b'directory')
             return _(b'unsupported file type (type is %s)') % kind
 
         badfn = match.bad
         dmap = self._map
         lstat = os.lstat
         getkind = stat.S_IFMT
         dirkind = stat.S_IFDIR
         regkind = stat.S_IFREG
         lnkkind = stat.S_IFLNK
         join = self._join
         dirsfound = []
         foundadd = dirsfound.append
         dirsnotfound = []
         notfoundadd = dirsnotfound.append
 
         if not match.isexact() and self._checkcase:
             normalize = self._normalize
         else:
             normalize = None
 
         files = sorted(match.files())
         subrepos.sort()
         i, j = 0, 0
         while i < len(files) and j < len(subrepos):
             subpath = subrepos[j] + b"/"
             if files[i] < subpath:
                 i += 1
                 continue
             while i < len(files) and files[i].startswith(subpath):
                 del files[i]
             j += 1
 
         if not files or b'' in files:
             files = [b'']
             # constructing the foldmap is expensive, so don't do it for the
             # common case where files is ['']
             normalize = None
         results = dict.fromkeys(subrepos)
         results[b'.hg'] = None
 
         for ff in files:
             if normalize:
                 nf = normalize(ff, False, True)
             else:
                 nf = ff
             if nf in results:
                 continue
 
             try:
                 st = lstat(join(nf))
                 kind = getkind(st.st_mode)
                 if kind == dirkind:
                     if nf in dmap:
                         # file replaced by dir on disk but still in dirstate
                         results[nf] = None
                     foundadd((nf, ff))
                 elif kind == regkind or kind == lnkkind:
                     results[nf] = st
                 else:
                     badfn(ff, badtype(kind))
                     if nf in dmap:
                         results[nf] = None
             except OSError as inst:  # nf not found on disk - it is dirstate only
                 if nf in dmap:  # does it exactly match a missing file?
                     results[nf] = None
                 else:  # does it match a missing directory?
                     if self._map.hasdir(nf):
                         notfoundadd(nf)
                     else:
                         badfn(ff, encoding.strtolocal(inst.strerror))
 
         # match.files() may contain explicitly-specified paths that shouldn't
         # be taken; drop them from the list of files found. dirsfound/notfound
         # aren't filtered here because they will be tested later.
         if match.anypats():
             for f in list(results):
                 if f == b'.hg' or f in subrepos:
                     # keep sentinel to disable further out-of-repo walks
                     continue
                 if not match(f):
                     del results[f]
 
         # Case insensitive filesystems cannot rely on lstat() failing to detect
         # a case-only rename.  Prune the stat object for any file that does not
         # match the case in the filesystem, if there are multiple files that
         # normalize to the same path.
         if match.isexact() and self._checkcase:
             normed = {}
 
             for f, st in pycompat.iteritems(results):
                 if st is None:
                     continue
 
                 nc = util.normcase(f)
                 paths = normed.get(nc)
 
                 if paths is None:
                     paths = set()
                     normed[nc] = paths
 
                 paths.add(f)
 
             for norm, paths in pycompat.iteritems(normed):
                 if len(paths) > 1:
                     for path in paths:
                         folded = self._discoverpath(
                             path, norm, True, None, self._map.dirfoldmap
                         )
                         if path != folded:
                             results[path] = None
 
         return results, dirsfound, dirsnotfound
 
     def walk(self, match, subrepos, unknown, ignored, full=True):
         """
         Walk recursively through the directory tree, finding all files
         matched by match.
 
         If full is False, maybe skip some known-clean files.
 
         Return a dict mapping filename to stat-like object (either
         mercurial.osutil.stat instance or return value of os.stat()).
 
         """
         # full is a flag that extensions that hook into walk can use -- this
         # implementation doesn't use it at all. This satisfies the contract
         # because we only guarantee a "maybe".
 
         if ignored:
             ignore = util.never
             dirignore = util.never
         elif unknown:
             ignore = self._ignore
             dirignore = self._dirignore
         else:
             # if not unknown and not ignored, drop dir recursion and step 2
             ignore = util.always
             dirignore = util.always
 
         matchfn = match.matchfn
         matchalways = match.always()
         matchtdir = match.traversedir
         dmap = self._map
         listdir = util.listdir
         lstat = os.lstat
         dirkind = stat.S_IFDIR
         regkind = stat.S_IFREG
         lnkkind = stat.S_IFLNK
         join = self._join
 
         exact = skipstep3 = False
         if match.isexact():  # match.exact
             exact = True
             dirignore = util.always  # skip step 2
         elif match.prefix():  # match.match, no patterns
             skipstep3 = True
 
         if not exact and self._checkcase:
             normalize = self._normalize
             normalizefile = self._normalizefile
             skipstep3 = False
         else:
             normalize = self._normalize
             normalizefile = None
 
         # step 1: find all explicit files
         results, work, dirsnotfound = self._walkexplicit(match, subrepos)
         if matchtdir:
             for d in work:
                 matchtdir(d[0])
             for d in dirsnotfound:
                 matchtdir(d)
 
         skipstep3 = skipstep3 and not (work or dirsnotfound)
         work = [d for d in work if not dirignore(d[0])]
 
         # step 2: visit subdirectories
         def traverse(work, alreadynormed):
             wadd = work.append
             while work:
                 tracing.counter('dirstate.walk work', len(work))
                 nd = work.pop()
                 visitentries = match.visitchildrenset(nd)
                 if not visitentries:
                     continue
                 if visitentries == b'this' or visitentries == b'all':
                     visitentries = None
                 skip = None
                 if nd != b'':
                     skip = b'.hg'
                 try:
                     with tracing.log('dirstate.walk.traverse listdir %s', nd):
                         entries = listdir(join(nd), stat=True, skip=skip)
                 except OSError as inst:
                     if inst.errno in (errno.EACCES, errno.ENOENT):
                         match.bad(
                             self.pathto(nd), encoding.strtolocal(inst.strerror)
                         )
                         continue
                     raise
                 for f, kind, st in entries:
                     # Some matchers may return files in the visitentries set,
                     # instead of 'this', if the matcher explicitly mentions them
                     # and is not an exactmatcher. This is acceptable; we do not
                     # make any hard assumptions about file-or-directory below
                     # based on the presence of `f` in visitentries. If
                     # visitchildrenset returned a set, we can always skip the
                     # entries *not* in the set it provided regardless of whether
                     # they're actually a file or a directory.
                     if visitentries and f not in visitentries:
                         continue
                     if normalizefile:
                         # even though f might be a directory, we're only
                         # interested in comparing it to files currently in the
                         # dmap -- therefore normalizefile is enough
                         nf = normalizefile(
                             nd and (nd + b"/" + f) or f, True, True
                         )
                     else:
                         nf = nd and (nd + b"/" + f) or f
                     if nf not in results:
                         if kind == dirkind:
                             if not ignore(nf):
                                 if matchtdir:
                                     matchtdir(nf)
                                 wadd(nf)
                             if nf in dmap and (matchalways or matchfn(nf)):
                                 results[nf] = None
                         elif kind == regkind or kind == lnkkind:
                             if nf in dmap:
                                 if matchalways or matchfn(nf):
                                     results[nf] = st
                             elif (matchalways or matchfn(nf)) and not ignore(
                                 nf
                             ):
                                 # unknown file -- normalize if necessary
                                 if not alreadynormed:
                                     nf = normalize(nf, False, True)
                                 results[nf] = st
                         elif nf in dmap and (matchalways or matchfn(nf)):
                             results[nf] = None
 
         for nd, d in work:
             # alreadynormed means that processwork doesn't have to do any
             # expensive directory normalization
             alreadynormed = not normalize or nd == d
             traverse([d], alreadynormed)
 
         for s in subrepos:
             del results[s]
         del results[b'.hg']
 
         # step 3: visit remaining files from dmap
         if not skipstep3 and not exact:
             # If a dmap file is not in results yet, it was either
             # a) not matching matchfn b) ignored, c) missing, or d) under a
             # symlink directory.
             if not results and matchalways:
                 visit = [f for f in dmap]
             else:
                 visit = [f for f in dmap if f not in results and matchfn(f)]
             visit.sort()
 
             if unknown:
                 # unknown == True means we walked all dirs under the roots
                 # that wasn't ignored, and everything that matched was stat'ed
                 # and is already in results.
                 # The rest must thus be ignored or under a symlink.
                 audit_path = pathutil.pathauditor(self._root, cached=True)
 
                 for nf in iter(visit):
                     # If a stat for the same file was already added with a
                     # different case, don't add one for this, since that would
                     # make it appear as if the file exists under both names
                     # on disk.
                     if (
                         normalizefile
                         and normalizefile(nf, True, True) in results
                     ):
                         results[nf] = None
                     # Report ignored items in the dmap as long as they are not
                     # under a symlink directory.
                     elif audit_path.check(nf):
                         try:
                             results[nf] = lstat(join(nf))
                             # file was just ignored, no links, and exists
                         except OSError:
                             # file doesn't exist
                             results[nf] = None
                     else:
                         # It's either missing or under a symlink directory
                         # which we in this case report as missing
                         results[nf] = None
             else:
                 # We may not have walked the full directory tree above,
                 # so stat and check everything we missed.
                 iv = iter(visit)
                 for st in util.statfiles([join(i) for i in visit]):
                     results[next(iv)] = st
         return results
 
     def _rust_status(self, matcher, list_clean, list_ignored, list_unknown):
         # Force Rayon (Rust parallelism library) to respect the number of
         # workers. This is a temporary workaround until Rust code knows
         # how to read the config file.
         numcpus = self._ui.configint(b"worker", b"numcpus")
         if numcpus is not None:
             encoding.environ.setdefault(b'RAYON_NUM_THREADS', b'%d' % numcpus)
 
         workers_enabled = self._ui.configbool(b"worker", b"enabled", True)
         if not workers_enabled:
             encoding.environ[b"RAYON_NUM_THREADS"] = b"1"
 
         (
             lookup,
             modified,
             added,
             removed,
             deleted,
             clean,
             ignored,
             unknown,
             warnings,
             bad,
             traversed,
             dirty,
         ) = rustmod.status(
             self._map._rustmap,
             matcher,
             self._rootdir,
             self._ignorefiles(),
             self._checkexec,
             self._lastnormaltime,
             bool(list_clean),
             bool(list_ignored),
             bool(list_unknown),
             bool(matcher.traversedir),
         )
 
         self._dirty |= dirty
 
         if matcher.traversedir:
             for dir in traversed:
                 matcher.traversedir(dir)
 
         if self._ui.warn:
             for item in warnings:
                 if isinstance(item, tuple):
                     file_path, syntax = item
                     msg = _(b"%s: ignoring invalid syntax '%s'\n") % (
                         file_path,
                         syntax,
                     )
                     self._ui.warn(msg)
                 else:
                     msg = _(b"skipping unreadable pattern file '%s': %s\n")
                     self._ui.warn(
                         msg
                         % (
                             pathutil.canonpath(
                                 self._rootdir, self._rootdir, item
                             ),
                             b"No such file or directory",
                         )
                     )
 
         for (fn, message) in bad:
             matcher.bad(fn, encoding.strtolocal(message))
 
         status = scmutil.status(
             modified=modified,
             added=added,
             removed=removed,
             deleted=deleted,
             unknown=unknown,
             ignored=ignored,
             clean=clean,
         )
         return (lookup, status)
 
     def status(self, match, subrepos, ignored, clean, unknown):
         """Determine the status of the working copy relative to the
         dirstate and return a pair of (unsure, status), where status is of type
         scmutil.status and:
 
           unsure:
             files that might have been modified since the dirstate was
             written, but need to be read to be sure (size is the same
             but mtime differs)
           status.modified:
             files that have definitely been modified since the dirstate
             was written (different size or mode)
           status.clean:
             files that have definitely not been modified since the
             dirstate was written
         """
         listignored, listclean, listunknown = ignored, clean, unknown
         lookup, modified, added, unknown, ignored = [], [], [], [], []
         removed, deleted, clean = [], [], []
 
         dmap = self._map
         dmap.preload()
 
         use_rust = True
 
         allowed_matchers = (
             matchmod.alwaysmatcher,
             matchmod.exactmatcher,
             matchmod.includematcher,
         )
 
         if rustmod is None:
             use_rust = False
         elif self._checkcase:
             # Case-insensitive filesystems are not handled yet
             use_rust = False
         elif subrepos:
             use_rust = False
         elif sparse.enabled:
             use_rust = False
         elif not isinstance(match, allowed_matchers):
             # Some matchers have yet to be implemented
             use_rust = False
 
         if use_rust:
             try:
                 return self._rust_status(
                     match, listclean, listignored, listunknown
                 )
             except rustmod.FallbackError:
                 pass
 
         def noop(f):
             pass
 
         dcontains = dmap.__contains__
         dget = dmap.__getitem__
         ladd = lookup.append  # aka "unsure"
         madd = modified.append
         aadd = added.append
         uadd = unknown.append if listunknown else noop
         iadd = ignored.append if listignored else noop
         radd = removed.append
         dadd = deleted.append
         cadd = clean.append if listclean else noop
         mexact = match.exact
         dirignore = self._dirignore
         checkexec = self._checkexec
         copymap = self._map.copymap
         lastnormaltime = self._lastnormaltime
 
         # We need to do full walks when either
         # - we're listing all clean files, or
         # - match.traversedir does something, because match.traversedir should
         #   be called for every dir in the working dir
         full = listclean or match.traversedir is not None
         for fn, st in pycompat.iteritems(
             self.walk(match, subrepos, listunknown, listignored, full=full)
         ):
             if not dcontains(fn):
                 if (listignored or mexact(fn)) and dirignore(fn):
                     if listignored:
                         iadd(fn)
                 else:
                     uadd(fn)
                 continue
 
             # This is equivalent to 'state, mode, size, time = dmap[fn]' but not
             # written like that for performance reasons. dmap[fn] is not a
             # Python tuple in compiled builds. The CPython UNPACK_SEQUENCE
             # opcode has fast paths when the value to be unpacked is a tuple or
             # a list, but falls back to creating a full-fledged iterator in
             # general. That is much slower than simply accessing and storing the
             # tuple members one by one.
             t = dget(fn)
             state = t.state
             mode = t[1]
             size = t[2]
             time = t[3]
 
             if not st and state in b"nma":
                 dadd(fn)
             elif state == b'n':
                 if (
                     size >= 0
                     and (
                         (size != st.st_size and size != st.st_size & _rangemask)
                         or ((mode ^ st.st_mode) & 0o100 and checkexec)
                     )
                     or t.from_p2
                     or fn in copymap
                 ):
                     if stat.S_ISLNK(st.st_mode) and size != st.st_size:
                         # issue6456: Size returned may be longer due to
                         # encryption on EXT-4 fscrypt, undecided.
                         ladd(fn)
                     else:
                         madd(fn)
                 elif (
                     time != st[stat.ST_MTIME]
                     and time != st[stat.ST_MTIME] & _rangemask
                 ):
                     ladd(fn)
                 elif st[stat.ST_MTIME] == lastnormaltime:
                     # fn may have just been marked as normal and it may have
                     # changed in the same second without changing its size.
                     # This can happen if we quickly do multiple commits.
                     # Force lookup, so we don't miss such a racy file change.
                     ladd(fn)
                 elif listclean:
                     cadd(fn)
             elif t.merged:
                 madd(fn)
             elif state == b'a':
                 aadd(fn)
-            elif state == b'r':
+            elif t.removed:
                 radd(fn)
         status = scmutil.status(
             modified, added, removed, deleted, unknown, ignored, clean
         )
         return (lookup, status)
 
     def matches(self, match):
         """
         return files in the dirstate (in whatever state) filtered by match
         """
         dmap = self._map
         if rustmod is not None:
             dmap = self._map._rustmap
 
         if match.always():
             return dmap.keys()
         files = match.files()
         if match.isexact():
             # fast path -- filter the other way around, since typically files is
             # much smaller than dmap
             return [f for f in files if f in dmap]
         if match.prefix() and all(fn in dmap for fn in files):
             # fast path -- all the values are known to be files, so just return
             # that
             return list(files)
         return [f for f in dmap if match(f)]
 
     def _actualfilename(self, tr):
         if tr:
             return self._pendingfilename
         else:
             return self._filename
 
     def savebackup(self, tr, backupname):
         '''Save current dirstate into backup file'''
         filename = self._actualfilename(tr)
         assert backupname != filename
 
         # use '_writedirstate' instead of 'write' to write changes certainly,
         # because the latter omits writing out if transaction is running.
         # output file will be used to create backup of dirstate at this point.
         if self._dirty or not self._opener.exists(filename):
             self._writedirstate(
                 self._opener(filename, b"w", atomictemp=True, checkambig=True)
             )
 
         if tr:
             # ensure that subsequent tr.writepending returns True for
             # changes written out above, even if dirstate is never
             # changed after this
             tr.addfilegenerator(
                 b'dirstate',
                 (self._filename,),
                 self._writedirstate,
                 location=b'plain',
             )
 
             # ensure that pending file written above is unlinked at
             # failure, even if tr.writepending isn't invoked until the
             # end of this transaction
             tr.registertmp(filename, location=b'plain')
 
         self._opener.tryunlink(backupname)
         # hardlink backup is okay because _writedirstate is always called
         # with an "atomictemp=True" file.
         util.copyfile(
             self._opener.join(filename),
             self._opener.join(backupname),
             hardlink=True,
         )
 
     def restorebackup(self, tr, backupname):
         '''Restore dirstate by backup file'''
         # this "invalidate()" prevents "wlock.release()" from writing
         # changes of dirstate out after restoring from backup file
         self.invalidate()
         filename = self._actualfilename(tr)
         o = self._opener
         if util.samefile(o.join(backupname), o.join(filename)):
             o.unlink(backupname)
         else:
             o.rename(backupname, filename, checkambig=True)
 
     def clearbackup(self, tr, backupname):
         '''Clear backup file'''
         self._opener.unlink(backupname)

mercurial/pure/parsers.py

@@ -1,514 +1,519
 # parsers.py - Python implementation of parsers.c
 #
 # Copyright 2009 Olivia Mackall <[e-mail]> and others
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 from __future__ import absolute_import
 
 import struct
 import zlib
 
 from ..node import (
     nullrev,
     sha1nodeconstants,
 )
 from .. import (
     error,
     pycompat,
     revlogutils,
     util,
 )
 
 from ..revlogutils import nodemap as nodemaputil
 from ..revlogutils import constants as revlog_constants
 
 stringio = pycompat.bytesio
 
 
 _pack = struct.pack
 _unpack = struct.unpack
 _compress = zlib.compress
 _decompress = zlib.decompress
 
 
 # a special value used internally for `size` if the file come from the other parent
 FROM_P2 = -2
 
 
 class dirstatetuple(object):
     """represent a dirstate entry
 
     It contains:
 
     - state (one of 'n', 'a', 'r', 'm')
     - mode,
     - size,
     - mtime,
     """
 
     __slot__ = ('_state', '_mode', '_size', '_mtime')
 
     def __init__(self, state, mode, size, mtime):
         self._state = state
         self._mode = mode
         self._size = size
         self._mtime = mtime
 
     def __getitem__(self, idx):
         if idx == 0 or idx == -4:
             return self._state
         elif idx == 1 or idx == -3:
             return self._mode
         elif idx == 2 or idx == -2:
             return self._size
         elif idx == 3 or idx == -1:
             return self._mtime
         else:
             raise IndexError(idx)
 
     @property
     def state(self):
         """
         States are:
           n  normal
           m  needs merging
           r  marked for removal
           a  marked for addition
 
         XXX This "state" is a bit obscure and mostly a direct expression of the
         dirstatev1 format. It would make sense to ultimately deprecate it in
         favor of the more "semantic" attributes.
         """
         return self._state
 
     @property
     def merged(self):
         """True if the file has been merged
 
         Should only be set if a merge is in progress in the dirstate
         """
         return self._state == b'm'
 
     @property
     def from_p2(self):
         """True if the file have been fetched from p2 during the current merge
 
         Should only be set if a merge is in progress in the dirstate
         """
         return self._size == FROM_P2
 
+    @property
+    def removed(self):
+        """True if the file has been removed"""
+        return self._state == b'r'
+
     def v1_state(self):
         """return a "state" suitable for v1 serialization"""
         return self._state
 
     def v1_mode(self):
         """return a "mode" suitable for v1 serialization"""
         return self._mode
 
     def v1_size(self):
         """return a "size" suitable for v1 serialization"""
         return self._size
 
     def v1_mtime(self):
         """return a "mtime" suitable for v1 serialization"""
         return self._mtime
 
 
 def gettype(q):
     return int(q & 0xFFFF)
 
 
 class BaseIndexObject(object):
     # Can I be passed to an algorithme implemented in Rust ?
     rust_ext_compat = 0
     # Format of an index entry according to Python's `struct` language
     index_format = revlog_constants.INDEX_ENTRY_V1
     # Size of a C unsigned long long int, platform independent
     big_int_size = struct.calcsize(b'>Q')
     # Size of a C long int, platform independent
     int_size = struct.calcsize(b'>i')
     # An empty index entry, used as a default value to be overridden, or nullrev
     null_item = (
         0,
         0,
         0,
         -1,
         -1,
         -1,
         -1,
         sha1nodeconstants.nullid,
         0,
         0,
         revlog_constants.COMP_MODE_INLINE,
         revlog_constants.COMP_MODE_INLINE,
     )
 
     @util.propertycache
     def entry_size(self):
         return self.index_format.size
 
     @property
     def nodemap(self):
         msg = b"index.nodemap is deprecated, use index.[has_node|rev|get_rev]"
         util.nouideprecwarn(msg, b'5.3', stacklevel=2)
         return self._nodemap
 
     @util.propertycache
     def _nodemap(self):
         nodemap = nodemaputil.NodeMap({sha1nodeconstants.nullid: nullrev})
         for r in range(0, len(self)):
             n = self[r][7]
             nodemap[n] = r
         return nodemap
 
     def has_node(self, node):
         """return True if the node exist in the index"""
         return node in self._nodemap
 
     def rev(self, node):
         """return a revision for a node
 
         If the node is unknown, raise a RevlogError"""
         return self._nodemap[node]
 
     def get_rev(self, node):
         """return a revision for a node
 
         If the node is unknown, return None"""
         return self._nodemap.get(node)
 
     def _stripnodes(self, start):
         if '_nodemap' in vars(self):
             for r in range(start, len(self)):
                 n = self[r][7]
                 del self._nodemap[n]
 
     def clearcaches(self):
         self.__dict__.pop('_nodemap', None)
 
     def __len__(self):
         return self._lgt + len(self._extra)
 
     def append(self, tup):
         if '_nodemap' in vars(self):
             self._nodemap[tup[7]] = len(self)
         data = self._pack_entry(len(self), tup)
         self._extra.append(data)
 
     def _pack_entry(self, rev, entry):
         assert entry[8] == 0
         assert entry[9] == 0
         return self.index_format.pack(*entry[:8])
 
     def _check_index(self, i):
         if not isinstance(i, int):
             raise TypeError(b"expecting int indexes")
         if i < 0 or i >= len(self):
             raise IndexError
 
     def __getitem__(self, i):
         if i == -1:
             return self.null_item
         self._check_index(i)
         if i >= self._lgt:
             data = self._extra[i - self._lgt]
         else:
             index = self._calculate_index(i)
             data = self._data[index : index + self.entry_size]
         r = self._unpack_entry(i, data)
         if self._lgt and i == 0:
             offset = revlogutils.offset_type(0, gettype(r[0]))
             r = (offset,) + r[1:]
         return r
 
     def _unpack_entry(self, rev, data):
         r = self.index_format.unpack(data)
         r = r + (
             0,
             0,
             revlog_constants.COMP_MODE_INLINE,
             revlog_constants.COMP_MODE_INLINE,
         )
         return r
 
     def pack_header(self, header):
         """pack header information as binary"""
         v_fmt = revlog_constants.INDEX_HEADER
         return v_fmt.pack(header)
 
     def entry_binary(self, rev):
         """return the raw binary string representing a revision"""
         entry = self[rev]
         p = revlog_constants.INDEX_ENTRY_V1.pack(*entry[:8])
         if rev == 0:
             p = p[revlog_constants.INDEX_HEADER.size :]
         return p
 
 
 class IndexObject(BaseIndexObject):
     def __init__(self, data):
         assert len(data) % self.entry_size == 0, (
             len(data),
             self.entry_size,
             len(data) % self.entry_size,
         )
         self._data = data
         self._lgt = len(data) // self.entry_size
         self._extra = []
 
     def _calculate_index(self, i):
         return i * self.entry_size
 
     def __delitem__(self, i):
         if not isinstance(i, slice) or not i.stop == -1 or i.step is not None:
             raise ValueError(b"deleting slices only supports a:-1 with step 1")
         i = i.start
         self._check_index(i)
         self._stripnodes(i)
         if i < self._lgt:
             self._data = self._data[: i * self.entry_size]
             self._lgt = i
             self._extra = []
         else:
             self._extra = self._extra[: i - self._lgt]
 
 
 class PersistentNodeMapIndexObject(IndexObject):
     """a Debug oriented class to test persistent nodemap
 
     We need a simple python object to test API and higher level behavior. See
     the Rust implementation for  more serious usage. This should be used only
     through the dedicated `devel.persistent-nodemap` config.
     """
 
     def nodemap_data_all(self):
         """Return bytes containing a full serialization of a nodemap
 
         The nodemap should be valid for the full set of revisions in the
         index."""
         return nodemaputil.persistent_data(self)
 
     def nodemap_data_incremental(self):
         """Return bytes containing a incremental update to persistent nodemap
 
         This containst the data for an append-only update of the data provided
         in the last call to `update_nodemap_data`.
         """
         if self._nm_root is None:
             return None
         docket = self._nm_docket
         changed, data = nodemaputil.update_persistent_data(
             self, self._nm_root, self._nm_max_idx, self._nm_docket.tip_rev
         )
 
         self._nm_root = self._nm_max_idx = self._nm_docket = None
         return docket, changed, data
 
     def update_nodemap_data(self, docket, nm_data):
         """provide full block of persisted binary data for a nodemap
 
         The data are expected to come from disk. See `nodemap_data_all` for a
         produceur of such data."""
         if nm_data is not None:
             self._nm_root, self._nm_max_idx = nodemaputil.parse_data(nm_data)
             if self._nm_root:
                 self._nm_docket = docket
             else:
                 self._nm_root = self._nm_max_idx = self._nm_docket = None
 
 
 class InlinedIndexObject(BaseIndexObject):
     def __init__(self, data, inline=0):
         self._data = data
         self._lgt = self._inline_scan(None)
         self._inline_scan(self._lgt)
         self._extra = []
 
     def _inline_scan(self, lgt):
         off = 0
         if lgt is not None:
             self._offsets = [0] * lgt
         count = 0
         while off <= len(self._data) - self.entry_size:
             start = off + self.big_int_size
             (s,) = struct.unpack(
                 b'>i',
                 self._data[start : start + self.int_size],
             )
             if lgt is not None:
                 self._offsets[count] = off
             count += 1
             off += self.entry_size + s
         if off != len(self._data):
             raise ValueError(b"corrupted data")
         return count
 
     def __delitem__(self, i):
         if not isinstance(i, slice) or not i.stop == -1 or i.step is not None:
             raise ValueError(b"deleting slices only supports a:-1 with step 1")
         i = i.start
         self._check_index(i)
         self._stripnodes(i)
         if i < self._lgt:
             self._offsets = self._offsets[:i]
             self._lgt = i
             self._extra = []
         else:
             self._extra = self._extra[: i - self._lgt]
 
     def _calculate_index(self, i):
         return self._offsets[i]
 
 
 def parse_index2(data, inline, revlogv2=False):
     if not inline:
         cls = IndexObject2 if revlogv2 else IndexObject
         return cls(data), None
     cls = InlinedIndexObject
     return cls(data, inline), (0, data)
 
 
 def parse_index_cl_v2(data):
     return IndexChangelogV2(data), None
 
 
 class IndexObject2(IndexObject):
     index_format = revlog_constants.INDEX_ENTRY_V2
 
     def replace_sidedata_info(
         self,
         rev,
         sidedata_offset,
         sidedata_length,
         offset_flags,
         compression_mode,
     ):
         """
         Replace an existing index entry's sidedata offset and length with new
         ones.
         This cannot be used outside of the context of sidedata rewriting,
         inside the transaction that creates the revision `rev`.
         """
         if rev < 0:
             raise KeyError
         self._check_index(rev)
         if rev < self._lgt:
             msg = b"cannot rewrite entries outside of this transaction"
             raise KeyError(msg)
         else:
             entry = list(self[rev])
             entry[0] = offset_flags
             entry[8] = sidedata_offset
             entry[9] = sidedata_length
             entry[11] = compression_mode
             entry = tuple(entry)
             new = self._pack_entry(rev, entry)
             self._extra[rev - self._lgt] = new
 
     def _unpack_entry(self, rev, data):
         data = self.index_format.unpack(data)
         entry = data[:10]
         data_comp = data[10] & 3
         sidedata_comp = (data[10] & (3 << 2)) >> 2
         return entry + (data_comp, sidedata_comp)
 
     def _pack_entry(self, rev, entry):
         data = entry[:10]
         data_comp = entry[10] & 3
         sidedata_comp = (entry[11] & 3) << 2
         data += (data_comp | sidedata_comp,)
 
         return self.index_format.pack(*data)
 
     def entry_binary(self, rev):
         """return the raw binary string representing a revision"""
         entry = self[rev]
         return self._pack_entry(rev, entry)
 
     def pack_header(self, header):
         """pack header information as binary"""
         msg = 'version header should go in the docket, not the index: %d'
         msg %= header
         raise error.ProgrammingError(msg)
 
 
 class IndexChangelogV2(IndexObject2):
     index_format = revlog_constants.INDEX_ENTRY_CL_V2
 
     def _unpack_entry(self, rev, data, r=True):
         items = self.index_format.unpack(data)
         entry = items[:3] + (rev, rev) + items[3:8]
         data_comp = items[8] & 3
         sidedata_comp = (items[8] >> 2) & 3
         return entry + (data_comp, sidedata_comp)
 
     def _pack_entry(self, rev, entry):
         assert entry[3] == rev, entry[3]
         assert entry[4] == rev, entry[4]
         data = entry[:3] + entry[5:10]
         data_comp = entry[10] & 3
         sidedata_comp = (entry[11] & 3) << 2
         data += (data_comp | sidedata_comp,)
         return self.index_format.pack(*data)
 
 
 def parse_index_devel_nodemap(data, inline):
     """like parse_index2, but alway return a PersistentNodeMapIndexObject"""
     return PersistentNodeMapIndexObject(data), None
 
 
 def parse_dirstate(dmap, copymap, st):
     parents = [st[:20], st[20:40]]
     # dereference fields so they will be local in loop
     format = b">cllll"
     e_size = struct.calcsize(format)
     pos1 = 40
     l = len(st)
 
     # the inner loop
     while pos1 < l:
         pos2 = pos1 + e_size
         e = _unpack(b">cllll", st[pos1:pos2])  # a literal here is faster
         pos1 = pos2 + e[4]
         f = st[pos2:pos1]
         if b'\0' in f:
             f, c = f.split(b'\0')
             copymap[f] = c
         dmap[f] = dirstatetuple(*e[:4])
     return parents
 
 
 def pack_dirstate(dmap, copymap, pl, now):
     now = int(now)
     cs = stringio()
     write = cs.write
     write(b"".join(pl))
     for f, e in pycompat.iteritems(dmap):
         if e[0] == b'n' and e[3] == now:
             # The file was last modified "simultaneously" with the current
             # write to dirstate (i.e. within the same second for file-
             # systems with a granularity of 1 sec). This commonly happens
             # for at least a couple of files on 'update'.
             # The user could change the file without changing its size
             # within the same second. Invalidate the file's mtime in
             # dirstate, forcing future 'status' calls to compare the
             # contents of the file if the size is the same. This prevents
             # mistakenly treating such files as clean.
             e = dirstatetuple(e[0], e[1], e[2], -1)
             dmap[f] = e
 
         if f in copymap:
             f = b"%s\0%s" % (f, copymap[f])
         e = _pack(
             b">cllll",
             e.v1_state(),
             e.v1_mode(),
             e.v1_size(),
             e.v1_mtime(),
             len(f),
         )
         write(e)
         write(f)
     return cs.getvalue()