dirstate-item: move the C implementation to the same logic

Now that we know were we are going, we can update the C implementation.

Differential Revision: https://phab.mercurial-scm.org/D11387

mercurial/cext/charencode.c

@@ -1,413 +1,413 b''
 /*
  charencode.c - miscellaneous character encoding
 
  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 <assert.h>
 
 #include "charencode.h"
 #include "compat.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_Type PyLong_Type
 #define PyInt_AS_LONG PyLong_AS_LONG
 #endif
 
 /* clang-format off */
 static const char lowertable[128] = {
 	'\x00', '\x01', '\x02', '\x03', '\x04', '\x05', '\x06', '\x07',
 	'\x08', '\x09', '\x0a', '\x0b', '\x0c', '\x0d', '\x0e', '\x0f',
 	'\x10', '\x11', '\x12', '\x13', '\x14', '\x15', '\x16', '\x17',
 	'\x18', '\x19', '\x1a', '\x1b', '\x1c', '\x1d', '\x1e', '\x1f',
 	'\x20', '\x21', '\x22', '\x23', '\x24', '\x25', '\x26', '\x27',
 	'\x28', '\x29', '\x2a', '\x2b', '\x2c', '\x2d', '\x2e', '\x2f',
 	'\x30', '\x31', '\x32', '\x33', '\x34', '\x35', '\x36', '\x37',
 	'\x38', '\x39', '\x3a', '\x3b', '\x3c', '\x3d', '\x3e', '\x3f',
 	'\x40',
 	        '\x61', '\x62', '\x63', '\x64', '\x65', '\x66', '\x67', /* A-G */
 	'\x68', '\x69', '\x6a', '\x6b', '\x6c', '\x6d', '\x6e', '\x6f', /* H-O */
 	'\x70', '\x71', '\x72', '\x73', '\x74', '\x75', '\x76', '\x77', /* P-W */
 	'\x78', '\x79', '\x7a',                                         /* X-Z */
 	                        '\x5b', '\x5c', '\x5d', '\x5e', '\x5f',
 	'\x60', '\x61', '\x62', '\x63', '\x64', '\x65', '\x66', '\x67',
 	'\x68', '\x69', '\x6a', '\x6b', '\x6c', '\x6d', '\x6e', '\x6f',
 	'\x70', '\x71', '\x72', '\x73', '\x74', '\x75', '\x76', '\x77',
 	'\x78', '\x79', '\x7a', '\x7b', '\x7c', '\x7d', '\x7e', '\x7f'
 };
 
 static const char uppertable[128] = {
 	'\x00', '\x01', '\x02', '\x03', '\x04', '\x05', '\x06', '\x07',
 	'\x08', '\x09', '\x0a', '\x0b', '\x0c', '\x0d', '\x0e', '\x0f',
 	'\x10', '\x11', '\x12', '\x13', '\x14', '\x15', '\x16', '\x17',
 	'\x18', '\x19', '\x1a', '\x1b', '\x1c', '\x1d', '\x1e', '\x1f',
 	'\x20', '\x21', '\x22', '\x23', '\x24', '\x25', '\x26', '\x27',
 	'\x28', '\x29', '\x2a', '\x2b', '\x2c', '\x2d', '\x2e', '\x2f',
 	'\x30', '\x31', '\x32', '\x33', '\x34', '\x35', '\x36', '\x37',
 	'\x38', '\x39', '\x3a', '\x3b', '\x3c', '\x3d', '\x3e', '\x3f',
 	'\x40', '\x41', '\x42', '\x43', '\x44', '\x45', '\x46', '\x47',
 	'\x48', '\x49', '\x4a', '\x4b', '\x4c', '\x4d', '\x4e', '\x4f',
 	'\x50', '\x51', '\x52', '\x53', '\x54', '\x55', '\x56', '\x57',
 	'\x58', '\x59', '\x5a', '\x5b', '\x5c', '\x5d', '\x5e', '\x5f',
 	'\x60',
 		'\x41', '\x42', '\x43', '\x44', '\x45', '\x46', '\x47', /* a-g */
 	'\x48', '\x49', '\x4a', '\x4b', '\x4c', '\x4d', '\x4e', '\x4f', /* h-o */
 	'\x50', '\x51', '\x52', '\x53', '\x54', '\x55', '\x56', '\x57', /* p-w */
 	'\x58', '\x59', '\x5a', 					/* x-z */
 				'\x7b', '\x7c', '\x7d', '\x7e', '\x7f'
 };
 
 /* 1: no escape, 2: \<c>, 6: \u<x> */
 static const uint8_t jsonlentable[256] = {
 	6, 6, 6, 6, 6, 6, 6, 6, 2, 2, 2, 6, 2, 2, 6, 6, /* b, t, n, f, r */
 	6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6,
 	1, 1, 2, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, /* " */
 	1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
 	1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
 	1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 1, 1, 1, /* \\ */
 	1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
 	1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 6, /* DEL */
 	1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
 	1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
 	1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
 	1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
 	1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
 	1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
 	1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
 	1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
 };
 
 static const uint8_t jsonparanoidlentable[128] = {
 	6, 6, 6, 6, 6, 6, 6, 6, 2, 2, 2, 6, 2, 2, 6, 6, /* b, t, n, f, r */
 	6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6,
 	1, 1, 2, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, /* " */
 	1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 6, 1, 6, 1, /* <, > */
 	1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
 	1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 1, 1, 1, /* \\ */
 	1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
 	1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 6, /* DEL */
 };
 
 static const char hexchartable[16] = {
 	'0', '1', '2', '3', '4', '5', '6', '7',
 	'8', '9', 'a', 'b', 'c', 'd', 'e', 'f',
 };
 /* clang-format on */
 
 /*
  * Turn a hex-encoded string into binary.
  */
 PyObject *unhexlify(const char *str, Py_ssize_t len)
 {
 	PyObject *ret;
 	char *d;
 	Py_ssize_t i;
 
 	ret = PyBytes_FromStringAndSize(NULL, len / 2);
 
 	if (!ret) {
 		return NULL;
 	}
 
 	d = PyBytes_AsString(ret);
 
 	for (i = 0; i < len;) {
 		int hi = hexdigit(str, i++);
 		int lo = hexdigit(str, i++);
 		*d++ = (hi << 4) | lo;
 	}
 
 	return ret;
 }
 
 PyObject *isasciistr(PyObject *self, PyObject *args)
 {
 	const char *buf;
 	Py_ssize_t i, len;
 	if (!PyArg_ParseTuple(args, PY23("s#:isasciistr", "y#:isasciistr"),
 	                      &buf, &len)) {
 		return NULL;
 	}
 	i = 0;
 	/* char array in PyStringObject should be at least 4-byte aligned */
 	if (((uintptr_t)buf & 3) == 0) {
 		const uint32_t *p = (const uint32_t *)buf;
 		for (; i < len / 4; i++) {
 			if (p[i] & 0x80808080U) {
 				Py_RETURN_FALSE;
 			}
 		}
 		i *= 4;
 	}
 	for (; i < len; i++) {
 		if (buf[i] & 0x80) {
 			Py_RETURN_FALSE;
 		}
 	}
 	Py_RETURN_TRUE;
 }
 
 static inline PyObject *
 _asciitransform(PyObject *str_obj, const char table[128], PyObject *fallback_fn)
 {
 	char *str, *newstr;
 	Py_ssize_t i, len;
 	PyObject *newobj = NULL;
 	PyObject *ret = NULL;
 
 	str = PyBytes_AS_STRING(str_obj);
 	len = PyBytes_GET_SIZE(str_obj);
 
 	newobj = PyBytes_FromStringAndSize(NULL, len);
 	if (!newobj) {
 		goto quit;
 	}
 
 	newstr = PyBytes_AS_STRING(newobj);
 
 	for (i = 0; i < len; i++) {
 		char c = str[i];
 		if (c & 0x80) {
 			if (fallback_fn != NULL) {
 				ret = PyObject_CallFunctionObjArgs(
 				    fallback_fn, str_obj, NULL);
 			} else {
 				PyObject *err = PyUnicodeDecodeError_Create(
 				    "ascii", str, len, i, (i + 1),
 				    "unexpected code byte");
 				PyErr_SetObject(PyExc_UnicodeDecodeError, err);
 				Py_XDECREF(err);
 			}
 			goto quit;
 		}
 		newstr[i] = table[(unsigned char)c];
 	}
 
 	ret = newobj;
 	Py_INCREF(ret);
 quit:
 	Py_XDECREF(newobj);
 	return ret;
 }
 
 PyObject *asciilower(PyObject *self, PyObject *args)
 {
 	PyObject *str_obj;
 	if (!PyArg_ParseTuple(args, "O!:asciilower", &PyBytes_Type, &str_obj)) {
 		return NULL;
 	}
 	return _asciitransform(str_obj, lowertable, NULL);
 }
 
 PyObject *asciiupper(PyObject *self, PyObject *args)
 {
 	PyObject *str_obj;
 	if (!PyArg_ParseTuple(args, "O!:asciiupper", &PyBytes_Type, &str_obj)) {
 		return NULL;
 	}
 	return _asciitransform(str_obj, uppertable, NULL);
 }
 
 PyObject *make_file_foldmap(PyObject *self, PyObject *args)
 {
 	PyObject *dmap, *spec_obj, *normcase_fallback;
 	PyObject *file_foldmap = NULL;
 	enum normcase_spec spec;
 	PyObject *k, *v;
 	dirstateItemObject *tuple;
 	Py_ssize_t pos = 0;
 	const char *table;
 
 	if (!PyArg_ParseTuple(args, "O!O!O!:make_file_foldmap", &PyDict_Type,
 	                      &dmap, &PyInt_Type, &spec_obj, &PyFunction_Type,
 	                      &normcase_fallback)) {
 		goto quit;
 	}
 
 	spec = (int)PyInt_AS_LONG(spec_obj);
 	switch (spec) {
 	case NORMCASE_LOWER:
 		table = lowertable;
 		break;
 	case NORMCASE_UPPER:
 		table = uppertable;
 		break;
 	case NORMCASE_OTHER:
 		table = NULL;
 		break;
 	default:
 		PyErr_SetString(PyExc_TypeError, "invalid normcasespec");
 		goto quit;
 	}
 
 	/* Add some more entries to deal with additions outside this
 	   function. */
 	file_foldmap = _dict_new_presized((PyDict_Size(dmap) / 10) * 11);
 	if (file_foldmap == NULL) {
 		goto quit;
 	}
 
 	while (PyDict_Next(dmap, &pos, &k, &v)) {
 		if (!dirstate_tuple_check(v)) {
 			PyErr_SetString(PyExc_TypeError,
 			                "expected a dirstate tuple");
 			goto quit;
 		}
 
 		tuple = (dirstateItemObject *)v;
-		if (tuple->state != 'r') {
+		if (tuple->flags | dirstate_flag_wc_tracked) {
 			PyObject *normed;
 			if (table != NULL) {
 				normed = _asciitransform(k, table,
 				                         normcase_fallback);
 			} else {
 				normed = PyObject_CallFunctionObjArgs(
 				    normcase_fallback, k, NULL);
 			}
 
 			if (normed == NULL) {
 				goto quit;
 			}
 			if (PyDict_SetItem(file_foldmap, normed, k) == -1) {
 				Py_DECREF(normed);
 				goto quit;
 			}
 			Py_DECREF(normed);
 		}
 	}
 	return file_foldmap;
 quit:
 	Py_XDECREF(file_foldmap);
 	return NULL;
 }
 
 /* calculate length of JSON-escaped string; returns -1 if unsupported */
 static Py_ssize_t jsonescapelen(const char *buf, Py_ssize_t len, bool paranoid)
 {
 	Py_ssize_t i, esclen = 0;
 
 	if (paranoid) {
 		/* don't want to process multi-byte escapes in C */
 		for (i = 0; i < len; i++) {
 			char c = buf[i];
 			if (c & 0x80) {
 				PyErr_SetString(PyExc_ValueError,
 				                "cannot process non-ascii str");
 				return -1;
 			}
 			esclen += jsonparanoidlentable[(unsigned char)c];
 			if (esclen < 0) {
 				PyErr_SetString(PyExc_MemoryError,
 				                "overflow in jsonescapelen");
 				return -1;
 			}
 		}
 	} else {
 		for (i = 0; i < len; i++) {
 			char c = buf[i];
 			esclen += jsonlentable[(unsigned char)c];
 			if (esclen < 0) {
 				PyErr_SetString(PyExc_MemoryError,
 				                "overflow in jsonescapelen");
 				return -1;
 			}
 		}
 	}
 
 	return esclen;
 }
 
 /* map '\<c>' escape character */
 static char jsonescapechar2(char c)
 {
 	switch (c) {
 	case '\b':
 		return 'b';
 	case '\t':
 		return 't';
 	case '\n':
 		return 'n';
 	case '\f':
 		return 'f';
 	case '\r':
 		return 'r';
 	case '"':
 		return '"';
 	case '\\':
 		return '\\';
 	}
 	return '\0'; /* should not happen */
 }
 
 /* convert 'origbuf' to JSON-escaped form 'escbuf'; 'origbuf' should only
    include characters mappable by json(paranoid)lentable */
 static void encodejsonescape(char *escbuf, Py_ssize_t esclen,
                              const char *origbuf, Py_ssize_t origlen,
                              bool paranoid)
 {
 	const uint8_t *lentable =
 	    (paranoid) ? jsonparanoidlentable : jsonlentable;
 	Py_ssize_t i, j;
 
 	for (i = 0, j = 0; i < origlen; i++) {
 		char c = origbuf[i];
 		uint8_t l = lentable[(unsigned char)c];
 		assert(j + l <= esclen);
 		switch (l) {
 		case 1:
 			escbuf[j] = c;
 			break;
 		case 2:
 			escbuf[j] = '\\';
 			escbuf[j + 1] = jsonescapechar2(c);
 			break;
 		case 6:
 			memcpy(escbuf + j, "\\u00", 4);
 			escbuf[j + 4] = hexchartable[(unsigned char)c >> 4];
 			escbuf[j + 5] = hexchartable[(unsigned char)c & 0xf];
 			break;
 		}
 		j += l;
 	}
 }
 
 PyObject *jsonescapeu8fast(PyObject *self, PyObject *args)
 {
 	PyObject *origstr, *escstr;
 	const char *origbuf;
 	Py_ssize_t origlen, esclen;
 	int paranoid;
 	if (!PyArg_ParseTuple(args, "O!i:jsonescapeu8fast", &PyBytes_Type,
 	                      &origstr, &paranoid)) {
 		return NULL;
 	}
 
 	origbuf = PyBytes_AS_STRING(origstr);
 	origlen = PyBytes_GET_SIZE(origstr);
 	esclen = jsonescapelen(origbuf, origlen, paranoid);
 	if (esclen < 0) {
 		return NULL; /* unsupported char found or overflow */
 	}
 	if (origlen == esclen) {
 		Py_INCREF(origstr);
 		return origstr;
 	}
 
 	escstr = PyBytes_FromStringAndSize(NULL, esclen);
 	if (!escstr) {
 		return NULL;
 	}
 	encodejsonescape(PyBytes_AS_STRING(escstr), esclen, origbuf, origlen,
 	                 paranoid);
 
 	return escstr;
 }

mercurial/cext/dirs.c

@@ -1,329 +1,330 b''
 /*
  dirs.c - dynamic directory diddling for dirstates
 
  Copyright 2013 Facebook
 
  This software may be used and distributed according to the terms of
  the GNU General Public License, incorporated herein by reference.
 */
 
 #define PY_SSIZE_T_CLEAN
 #include <Python.h>
 #include <string.h>
 
 #include "util.h"
 
 #ifdef IS_PY3K
 #define PYLONG_VALUE(o) ((PyLongObject *)o)->ob_digit[0]
 #else
 #define PYLONG_VALUE(o) PyInt_AS_LONG(o)
 #endif
 
 /*
  * This is a multiset of directory names, built from the files that
  * appear in a dirstate or manifest.
  *
  * A few implementation notes:
  *
  * We modify Python integers for refcounting, but those integers are
  * never visible to Python code.
  */
 /* clang-format off */
 typedef struct {
 	PyObject_HEAD
 	PyObject *dict;
 } dirsObject;
 /* clang-format on */
 
 static inline Py_ssize_t _finddir(const char *path, Py_ssize_t pos)
 {
 	while (pos != -1) {
 		if (path[pos] == '/')
 			break;
 		pos -= 1;
 	}
 	if (pos == -1) {
 		return 0;
 	}
 
 	return pos;
 }
 
 /* Mercurial will fail to run on directory hierarchies deeper than
  * this constant, so we should try and keep this constant as big as
  * possible.
  */
 #define MAX_DIRS_DEPTH 2048
 
 static int _addpath(PyObject *dirs, PyObject *path)
 {
 	const char *cpath = PyBytes_AS_STRING(path);
 	Py_ssize_t pos = PyBytes_GET_SIZE(path);
 	PyObject *key = NULL;
 	int ret = -1;
 	size_t num_slashes = 0;
 
 	/* This loop is super critical for performance. That's why we inline
 	 * access to Python structs instead of going through a supported API.
 	 * The implementation, therefore, is heavily dependent on CPython
 	 * implementation details. We also commit violations of the Python
 	 * "protocol" such as mutating immutable objects. But since we only
 	 * mutate objects created in this function or in other well-defined
 	 * locations, the references are known so these violations should go
 	 * unnoticed. */
 	while ((pos = _finddir(cpath, pos - 1)) != -1) {
 		PyObject *val;
 		++num_slashes;
 		if (num_slashes > MAX_DIRS_DEPTH) {
 			PyErr_SetString(PyExc_ValueError,
 			                "Directory hierarchy too deep.");
 			goto bail;
 		}
 
 		/* Sniff for trailing slashes, a marker of an invalid input. */
 		if (pos > 0 && cpath[pos - 1] == '/') {
 			PyErr_SetString(
 			    PyExc_ValueError,
 			    "found invalid consecutive slashes in path");
 			goto bail;
 		}
 
 		key = PyBytes_FromStringAndSize(cpath, pos);
 		if (key == NULL)
 			goto bail;
 
 		val = PyDict_GetItem(dirs, key);
 		if (val != NULL) {
 			PYLONG_VALUE(val) += 1;
 			Py_CLEAR(key);
 			break;
 		}
 
 		/* Force Python to not reuse a small shared int. */
 #ifdef IS_PY3K
 		val = PyLong_FromLong(0x1eadbeef);
 #else
 		val = PyInt_FromLong(0x1eadbeef);
 #endif
 
 		if (val == NULL)
 			goto bail;
 
 		PYLONG_VALUE(val) = 1;
 		ret = PyDict_SetItem(dirs, key, val);
 		Py_DECREF(val);
 		if (ret == -1)
 			goto bail;
 		Py_CLEAR(key);
 	}
 	ret = 0;
 
 bail:
 	Py_XDECREF(key);
 
 	return ret;
 }
 
 static int _delpath(PyObject *dirs, PyObject *path)
 {
 	char *cpath = PyBytes_AS_STRING(path);
 	Py_ssize_t pos = PyBytes_GET_SIZE(path);
 	PyObject *key = NULL;
 	int ret = -1;
 
 	while ((pos = _finddir(cpath, pos - 1)) != -1) {
 		PyObject *val;
 
 		key = PyBytes_FromStringAndSize(cpath, pos);
 
 		if (key == NULL)
 			goto bail;
 
 		val = PyDict_GetItem(dirs, key);
 		if (val == NULL) {
 			PyErr_SetString(PyExc_ValueError,
 			                "expected a value, found none");
 			goto bail;
 		}
 
 		if (--PYLONG_VALUE(val) <= 0) {
 			if (PyDict_DelItem(dirs, key) == -1)
 				goto bail;
 		} else
 			break;
 		Py_CLEAR(key);
 	}
 	ret = 0;
 
 bail:
 	Py_XDECREF(key);
 
 	return ret;
 }
 
 static int dirs_fromdict(PyObject *dirs, PyObject *source, bool only_tracked)
 {
 	PyObject *key, *value;
 	Py_ssize_t pos = 0;
 
 	while (PyDict_Next(source, &pos, &key, &value)) {
 		if (!PyBytes_Check(key)) {
 			PyErr_SetString(PyExc_TypeError, "expected string key");
 			return -1;
 		}
 		if (only_tracked) {
 			if (!dirstate_tuple_check(value)) {
 				PyErr_SetString(PyExc_TypeError,
 				                "expected a dirstate tuple");
 				return -1;
 			}
-			if (((dirstateItemObject *)value)->state == 'r')
+			if (!(((dirstateItemObject *)value)->flags &
+			      dirstate_flag_wc_tracked))
 				continue;
 		}
 
 		if (_addpath(dirs, key) == -1)
 			return -1;
 	}
 
 	return 0;
 }
 
 static int dirs_fromiter(PyObject *dirs, PyObject *source)
 {
 	PyObject *iter, *item = NULL;
 	int ret;
 
 	iter = PyObject_GetIter(source);
 	if (iter == NULL)
 		return -1;
 
 	while ((item = PyIter_Next(iter)) != NULL) {
 		if (!PyBytes_Check(item)) {
 			PyErr_SetString(PyExc_TypeError, "expected string");
 			break;
 		}
 
 		if (_addpath(dirs, item) == -1)
 			break;
 		Py_CLEAR(item);
 	}
 
 	ret = PyErr_Occurred() ? -1 : 0;
 	Py_DECREF(iter);
 	Py_XDECREF(item);
 	return ret;
 }
 
 /*
  * Calculate a refcounted set of directory names for the files in a
  * dirstate.
  */
 static int dirs_init(dirsObject *self, PyObject *args, PyObject *kwargs)
 {
 	PyObject *dirs = NULL, *source = NULL;
 	int only_tracked = 0;
 	int ret = -1;
 	static char *keywords_name[] = {"map", "only_tracked", NULL};
 
 	self->dict = NULL;
 
 	if (!PyArg_ParseTupleAndKeywords(args, kwargs, "|Oi:__init__",
 	                                 keywords_name, &source, &only_tracked))
 		return -1;
 
 	dirs = PyDict_New();
 
 	if (dirs == NULL)
 		return -1;
 
 	if (source == NULL)
 		ret = 0;
 	else if (PyDict_Check(source))
 		ret = dirs_fromdict(dirs, source, (bool)only_tracked);
 	else if (only_tracked)
 		PyErr_SetString(PyExc_ValueError,
 		                "`only_tracked` is only supported "
 		                "with a dict source");
 	else
 		ret = dirs_fromiter(dirs, source);
 
 	if (ret == -1)
 		Py_XDECREF(dirs);
 	else
 		self->dict = dirs;
 
 	return ret;
 }
 
 PyObject *dirs_addpath(dirsObject *self, PyObject *args)
 {
 	PyObject *path;
 
 	if (!PyArg_ParseTuple(args, "O!:addpath", &PyBytes_Type, &path))
 		return NULL;
 
 	if (_addpath(self->dict, path) == -1)
 		return NULL;
 
 	Py_RETURN_NONE;
 }
 
 static PyObject *dirs_delpath(dirsObject *self, PyObject *args)
 {
 	PyObject *path;
 
 	if (!PyArg_ParseTuple(args, "O!:delpath", &PyBytes_Type, &path))
 		return NULL;
 
 	if (_delpath(self->dict, path) == -1)
 		return NULL;
 
 	Py_RETURN_NONE;
 }
 
 static int dirs_contains(dirsObject *self, PyObject *value)
 {
 	return PyBytes_Check(value) ? PyDict_Contains(self->dict, value) : 0;
 }
 
 static void dirs_dealloc(dirsObject *self)
 {
 	Py_XDECREF(self->dict);
 	PyObject_Del(self);
 }
 
 static PyObject *dirs_iter(dirsObject *self)
 {
 	return PyObject_GetIter(self->dict);
 }
 
 static PySequenceMethods dirs_sequence_methods;
 
 static PyMethodDef dirs_methods[] = {
     {"addpath", (PyCFunction)dirs_addpath, METH_VARARGS, "add a path"},
     {"delpath", (PyCFunction)dirs_delpath, METH_VARARGS, "remove a path"},
     {NULL} /* Sentinel */
 };
 
 static PyTypeObject dirsType = {PyVarObject_HEAD_INIT(NULL, 0)};
 
 void dirs_module_init(PyObject *mod)
 {
 	dirs_sequence_methods.sq_contains = (objobjproc)dirs_contains;
 	dirsType.tp_name = "parsers.dirs";
 	dirsType.tp_new = PyType_GenericNew;
 	dirsType.tp_basicsize = sizeof(dirsObject);
 	dirsType.tp_dealloc = (destructor)dirs_dealloc;
 	dirsType.tp_as_sequence = &dirs_sequence_methods;
 	dirsType.tp_flags = Py_TPFLAGS_DEFAULT;
 	dirsType.tp_doc = "dirs";
 	dirsType.tp_iter = (getiterfunc)dirs_iter;
 	dirsType.tp_methods = dirs_methods;
 	dirsType.tp_init = (initproc)dirs_init;
 
 	if (PyType_Ready(&dirsType) < 0)
 		return;
 	Py_INCREF(&dirsType);
 
 	PyModule_AddObject(mod, "dirs", (PyObject *)&dirsType);
 }

mercurial/cext/parsers.c

@@ -1,1193 +1,1303 b''
 /*
  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 const int dirstate_v1_nonnormal = -1;
 static const int ambiguous_time = -1;
 
 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 PyObject *dirstate_item_new(PyTypeObject *subtype, PyObject *args,
                                    PyObject *kwds)
 {
 	/* We do all the initialization here and not a tp_init function because
 	 * dirstate_item is immutable. */
 	dirstateItemObject *t;
 	int wc_tracked;
 	int p1_tracked;
 	int p2_tracked;
 	int merged;
 	int clean_p1;
 	int clean_p2;
 	int possibly_dirty;
 	PyObject *parentfiledata;
 	static char *keywords_name[] = {
 	    "wc_tracked",     "p1_tracked",     "p2_tracked",
 	    "merged",         "clean_p1",       "clean_p2",
 	    "possibly_dirty", "parentfiledata", NULL,
 	};
 	wc_tracked = 0;
 	p1_tracked = 0;
 	p2_tracked = 0;
 	merged = 0;
 	clean_p1 = 0;
 	clean_p2 = 0;
 	possibly_dirty = 0;
 	parentfiledata = Py_None;
 	if (!PyArg_ParseTupleAndKeywords(args, kwds, "iiiiiiiO", keywords_name,
 	                                 &wc_tracked, &p1_tracked, &p2_tracked,
 	                                 &merged, &clean_p1, &clean_p2,
 	                                 &possibly_dirty, &parentfiledata
 
 	                                 )) {
 		return NULL;
 	}
 	if (merged && (clean_p1 || clean_p2)) {
 		PyErr_SetString(PyExc_RuntimeError,
 		                "`merged` argument incompatible with "
 		                "`clean_p1`/`clean_p2`");
 		return NULL;
 	}
 	t = (dirstateItemObject *)subtype->tp_alloc(subtype, 1);
 	if (!t) {
 		return NULL;
 	}
-	t->state = 'r';
+
+	t->flags = 0;
+	if (wc_tracked) {
+		t->flags |= dirstate_flag_wc_tracked;
+	}
+	if (p1_tracked) {
+		t->flags |= dirstate_flag_p1_tracked;
+	}
+	if (p2_tracked) {
+		t->flags |= dirstate_flag_p2_tracked;
+	}
+	if (possibly_dirty) {
+		t->flags |= dirstate_flag_possibly_dirty;
+	}
+	if (merged) {
+		t->flags |= dirstate_flag_merged;
+	}
+	if (clean_p1) {
+		t->flags |= dirstate_flag_clean_p1;
+	}
+	if (clean_p2) {
+		t->flags |= dirstate_flag_clean_p2;
+	}
 	t->mode = 0;
 	t->size = dirstate_v1_nonnormal;
 	t->mtime = ambiguous_time;
-	if (!(p1_tracked || p2_tracked || wc_tracked)) {
-		/* Nothing special to do, file is untracked */
-	} else if (merged) {
-		t->state = 'm';
-		t->size = dirstate_v1_from_p2;
-		t->mtime = ambiguous_time;
-	} else if (!(p1_tracked || p2_tracked) && wc_tracked) {
-		t->state = 'a';
-		t->size = dirstate_v1_nonnormal;
-		t->mtime = ambiguous_time;
-	} else if ((p1_tracked || p2_tracked) && !wc_tracked) {
-		t->state = 'r';
-		t->size = 0;
-		t->mtime = 0;
-	} else if (clean_p2 && wc_tracked) {
-		t->state = 'n';
-		t->size = dirstate_v1_from_p2;
-		t->mtime = ambiguous_time;
-	} else if (!p1_tracked && p2_tracked && wc_tracked) {
-		t->state = 'n';
-		t->size = dirstate_v1_from_p2;
-		t->mtime = ambiguous_time;
-	} else if (possibly_dirty) {
-		t->state = 'n';
-		t->size = dirstate_v1_nonnormal;
-		t->mtime = ambiguous_time;
-	} else if (wc_tracked) {
-		/* this is a "normal" file */
-		if (parentfiledata == Py_None) {
-			PyErr_SetString(
-			    PyExc_RuntimeError,
-			    "failed to pass parentfiledata for a normal file");
-			return NULL;
-		}
+	if (parentfiledata != Py_None) {
 		if (!PyTuple_CheckExact(parentfiledata)) {
 			PyErr_SetString(
 			    PyExc_TypeError,
 			    "parentfiledata should be a Tuple or None");
 			return NULL;
 		}
-		t->state = 'n';
 		t->mode =
 		    (int)PyLong_AsLong(PyTuple_GetItem(parentfiledata, 0));
 		t->size =
 		    (int)PyLong_AsLong(PyTuple_GetItem(parentfiledata, 1));
 		t->mtime =
 		    (int)PyLong_AsLong(PyTuple_GetItem(parentfiledata, 2));
-	} else {
-		PyErr_SetString(PyExc_RuntimeError, "unreachable");
-		return NULL;
 	}
 	return (PyObject *)t;
 }
 
 static void dirstate_item_dealloc(PyObject *o)
 {
 	PyObject_Del(o);
 }
 
 static inline bool dirstate_item_c_tracked(dirstateItemObject *self)
 {
-	return (self->state == 'a' || self->state == 'm' || self->state == 'n');
+	return (self->flags & dirstate_flag_wc_tracked);
 }
 
 static inline bool dirstate_item_c_added(dirstateItemObject *self)
 {
-	return (self->state == 'a');
+	char mask = (dirstate_flag_wc_tracked | dirstate_flag_p1_tracked |
+	             dirstate_flag_p2_tracked);
+	char target = dirstate_flag_wc_tracked;
+	return (self->flags & mask) == target;
 }
 
 static inline bool dirstate_item_c_removed(dirstateItemObject *self)
 {
-	return (self->state == 'r');
+	if (self->flags & dirstate_flag_wc_tracked) {
+		return false;
+	}
+	return (self->flags &
+	        (dirstate_flag_p1_tracked | dirstate_flag_p2_tracked));
 }
 
 static inline bool dirstate_item_c_merged(dirstateItemObject *self)
 {
-	return (self->state == 'm');
+	return ((self->flags & dirstate_flag_wc_tracked) &&
+	        (self->flags & dirstate_flag_merged));
 }
 
 static inline bool dirstate_item_c_merged_removed(dirstateItemObject *self)
 {
-	return (self->state == 'r' && self->size == dirstate_v1_nonnormal);
+	if (!dirstate_item_c_removed(self)) {
+		return false;
+	}
+	return (self->flags & dirstate_flag_merged);
 }
 
 static inline bool dirstate_item_c_from_p2(dirstateItemObject *self)
 {
-	return (self->state == 'n' && self->size == dirstate_v1_from_p2);
+	if (!dirstate_item_c_tracked(self)) {
+		return false;
+	}
+	return (self->flags & dirstate_flag_clean_p2);
 }
 
 static inline bool dirstate_item_c_from_p2_removed(dirstateItemObject *self)
 {
-	return (self->state == 'r' && self->size == dirstate_v1_from_p2);
+	if (!dirstate_item_c_removed(self)) {
+		return false;
+	}
+	return (self->flags & dirstate_flag_clean_p2);
 }
 
 static inline char dirstate_item_c_v1_state(dirstateItemObject *self)
 {
-	return self->state;
+	if (self->flags & dirstate_flag_rust_special) {
+		return ' ';
+	} else if (dirstate_item_c_removed(self)) {
+		return 'r';
+	} else if (dirstate_item_c_merged(self)) {
+		return 'm';
+	} else if (dirstate_item_c_added(self)) {
+		return 'a';
+	} else {
+		return 'n';
+	}
 }
 
 static inline int dirstate_item_c_v1_mode(dirstateItemObject *self)
 {
 	return self->mode;
 }
 
 static inline int dirstate_item_c_v1_size(dirstateItemObject *self)
 {
-	return self->size;
+	if (self->flags & dirstate_flag_rust_special) {
+		return self->size;
+	} else if (dirstate_item_c_merged_removed(self)) {
+		return dirstate_v1_nonnormal;
+	} else if (dirstate_item_c_from_p2_removed(self)) {
+		return dirstate_v1_from_p2;
+	} else if (dirstate_item_c_removed(self)) {
+		return 0;
+	} else if (dirstate_item_c_merged(self)) {
+		return dirstate_v1_from_p2;
+	} else if (dirstate_item_c_added(self)) {
+		return dirstate_v1_nonnormal;
+	} else if (dirstate_item_c_from_p2(self)) {
+		return dirstate_v1_from_p2;
+	} else if (self->flags & dirstate_flag_possibly_dirty) {
+		return self->size; /* NON NORMAL ? */
+	} else {
+		return self->size;
+	}
 }
 
 static inline int dirstate_item_c_v1_mtime(dirstateItemObject *self)
 {
-	return self->mtime;
+	if (self->flags & dirstate_flag_rust_special) {
+		return self->mtime;
+	} else if (dirstate_item_c_removed(self)) {
+		return 0;
+	} else if (self->flags & dirstate_flag_possibly_dirty) {
+		return ambiguous_time;
+	} else if (dirstate_item_c_merged(self)) {
+		return ambiguous_time;
+	} else if (dirstate_item_c_added(self)) {
+		return ambiguous_time;
+	} else if (dirstate_item_c_from_p2(self)) {
+		return ambiguous_time;
+	} else {
+		return self->mtime;
+	}
 }
 
 static PyObject *dirstate_item_v1_state(dirstateItemObject *self)
 {
 	char state = dirstate_item_c_v1_state(self);
 	return PyBytes_FromStringAndSize(&state, 1);
 };
 
 static PyObject *dirstate_item_v1_mode(dirstateItemObject *self)
 {
 	return PyInt_FromLong(dirstate_item_c_v1_mode(self));
 };
 
 static PyObject *dirstate_item_v1_size(dirstateItemObject *self)
 {
 	return PyInt_FromLong(dirstate_item_c_v1_size(self));
 };
 
 static PyObject *dirstate_item_v1_mtime(dirstateItemObject *self)
 {
 	return PyInt_FromLong(dirstate_item_c_v1_mtime(self));
 };
 
 static PyObject *dirstate_item_need_delay(dirstateItemObject *self,
                                           PyObject *value)
 {
 	long now;
 	if (!pylong_to_long(value, &now)) {
 		return NULL;
 	}
 	if (dirstate_item_c_v1_state(self) == 'n' &&
 	    dirstate_item_c_v1_mtime(self) == now) {
 		Py_RETURN_TRUE;
 	} else {
 		Py_RETURN_FALSE;
 	}
 };
 
 /* This will never change since it's bound to V1
  */
 static inline dirstateItemObject *
 dirstate_item_from_v1_data(char state, int mode, int size, int mtime)
 {
 	dirstateItemObject *t =
 	    PyObject_New(dirstateItemObject, &dirstateItemType);
 	if (!t) {
 		return NULL;
 	}
-	t->state = state;
-	t->mode = mode;
-	t->size = size;
-	t->mtime = mtime;
+
+	if (state == 'm') {
+		t->flags =
+		    (dirstate_flag_wc_tracked | dirstate_flag_p1_tracked |
+		     dirstate_flag_p2_tracked | dirstate_flag_merged);
+		t->mode = 0;
+		t->size = dirstate_v1_from_p2;
+		t->mtime = ambiguous_time;
+	} else if (state == 'a') {
+		t->flags = dirstate_flag_wc_tracked;
+		t->mode = 0;
+		t->size = dirstate_v1_nonnormal;
+		t->mtime = ambiguous_time;
+	} else if (state == 'r') {
+		t->mode = 0;
+		t->size = 0;
+		t->mtime = 0;
+		if (size == dirstate_v1_nonnormal) {
+			t->flags =
+			    (dirstate_flag_p1_tracked |
+			     dirstate_flag_p2_tracked | dirstate_flag_merged);
+		} else if (size == dirstate_v1_from_p2) {
+			t->flags =
+			    (dirstate_flag_p2_tracked | dirstate_flag_clean_p2);
+		} else {
+			t->flags = dirstate_flag_p1_tracked;
+		}
+	} else if (state == 'n') {
+		if (size == dirstate_v1_from_p2) {
+			t->flags =
+			    (dirstate_flag_wc_tracked |
+			     dirstate_flag_p2_tracked | dirstate_flag_clean_p2);
+			t->mode = 0;
+			t->size = dirstate_v1_from_p2;
+			t->mtime = ambiguous_time;
+		} else if (size == dirstate_v1_nonnormal) {
+			t->flags = (dirstate_flag_wc_tracked |
+			            dirstate_flag_p1_tracked |
+			            dirstate_flag_possibly_dirty);
+			t->mode = 0;
+			t->size = dirstate_v1_nonnormal;
+			t->mtime = ambiguous_time;
+		} else if (mtime == ambiguous_time) {
+			t->flags = (dirstate_flag_wc_tracked |
+			            dirstate_flag_p1_tracked |
+			            dirstate_flag_possibly_dirty);
+			t->mode = mode;
+			t->size = size;
+			t->mtime = 0;
+		} else {
+			t->flags = (dirstate_flag_wc_tracked |
+			            dirstate_flag_p1_tracked);
+			t->mode = mode;
+			t->size = size;
+			t->mtime = mtime;
+		}
+	} else if (state == ' ') {
+		/* XXX Rust is using this special case, it should be clean up
+		 * later. */
+		t->flags = dirstate_flag_rust_special;
+		t->mode = mode;
+		t->size = size;
+		t->mtime = mtime;
+	} else {
+		PyErr_Format(PyExc_RuntimeError,
+		             "unknown state: `%c` (%d, %d, %d)", state, mode,
+		             size, mtime, NULL);
+		return NULL;
+	}
+
 	return t;
 }
 
 /* This will never change since it's bound to V1, unlike `dirstate_item_new` */
 static PyObject *dirstate_item_from_v1_meth(PyTypeObject *subtype,
                                             PyObject *args)
 {
 	/* We do all the initialization here and not a tp_init function because
 	 * dirstate_item is immutable. */
 	char state;
 	int size, mode, mtime;
 	if (!PyArg_ParseTuple(args, "ciii", &state, &mode, &size, &mtime)) {
 		return NULL;
 	}
 	return (PyObject *)dirstate_item_from_v1_data(state, mode, size, mtime);
 };
 
 /* constructor to help legacy API to build a new "added" item
 
 Should eventually be removed */
 static PyObject *dirstate_item_new_added(PyTypeObject *subtype)
 {
 	dirstateItemObject *t;
 	t = (dirstateItemObject *)subtype->tp_alloc(subtype, 1);
 	if (!t) {
 		return NULL;
 	}
-	t->state = 'a';
+	t->flags = dirstate_flag_wc_tracked;
 	t->mode = 0;
 	t->size = dirstate_v1_nonnormal;
 	t->mtime = ambiguous_time;
 	return (PyObject *)t;
 };
 
 /* constructor to help legacy API to build a new "merged" item
 
 Should eventually be removed */
 static PyObject *dirstate_item_new_merged(PyTypeObject *subtype)
 {
 	dirstateItemObject *t;
 	t = (dirstateItemObject *)subtype->tp_alloc(subtype, 1);
 	if (!t) {
 		return NULL;
 	}
-	t->state = 'm';
+	t->flags = (dirstate_flag_wc_tracked | dirstate_flag_p1_tracked |
+	            dirstate_flag_p2_tracked | dirstate_flag_merged);
 	t->mode = 0;
 	t->size = dirstate_v1_from_p2;
 	t->mtime = ambiguous_time;
 	return (PyObject *)t;
 };
 
 /* constructor to help legacy API to build a new "from_p2" item
 
 Should eventually be removed */
 static PyObject *dirstate_item_new_from_p2(PyTypeObject *subtype)
 {
 	/* We do all the initialization here and not a tp_init function because
 	 * dirstate_item is immutable. */
 	dirstateItemObject *t;
 	t = (dirstateItemObject *)subtype->tp_alloc(subtype, 1);
 	if (!t) {
 		return NULL;
 	}
-	t->state = 'n';
+	t->flags = (dirstate_flag_wc_tracked | dirstate_flag_p2_tracked |
+	            dirstate_flag_clean_p2);
 	t->mode = 0;
 	t->size = dirstate_v1_from_p2;
 	t->mtime = ambiguous_time;
 	return (PyObject *)t;
 };
 
 /* constructor to help legacy API to build a new "possibly" item
 
 Should eventually be removed */
 static PyObject *dirstate_item_new_possibly_dirty(PyTypeObject *subtype)
 {
 	/* We do all the initialization here and not a tp_init function because
 	 * dirstate_item is immutable. */
 	dirstateItemObject *t;
 	t = (dirstateItemObject *)subtype->tp_alloc(subtype, 1);
 	if (!t) {
 		return NULL;
 	}
-	t->state = 'n';
+	t->flags = (dirstate_flag_wc_tracked | dirstate_flag_p1_tracked |
+	            dirstate_flag_possibly_dirty);
 	t->mode = 0;
 	t->size = dirstate_v1_nonnormal;
 	t->mtime = ambiguous_time;
 	return (PyObject *)t;
 };
 
 /* constructor to help legacy API to build a new "normal" item
 
 Should eventually be removed */
 static PyObject *dirstate_item_new_normal(PyTypeObject *subtype, PyObject *args)
 {
 	/* We do all the initialization here and not a tp_init function because
 	 * dirstate_item is immutable. */
 	dirstateItemObject *t;
 	int size, mode, mtime;
 	if (!PyArg_ParseTuple(args, "iii", &mode, &size, &mtime)) {
 		return NULL;
 	}
 
 	t = (dirstateItemObject *)subtype->tp_alloc(subtype, 1);
 	if (!t) {
 		return NULL;
 	}
-	t->state = 'n';
+	t->flags = (dirstate_flag_wc_tracked | dirstate_flag_p1_tracked);
 	t->mode = mode;
 	t->size = size;
 	t->mtime = mtime;
 	return (PyObject *)t;
 };
 
 /* This means the next status call will have to actually check its content
    to make sure it is correct. */
 static PyObject *dirstate_item_set_possibly_dirty(dirstateItemObject *self)
 {
-	self->mtime = ambiguous_time;
-	Py_RETURN_NONE;
+	if (self->flags |= dirstate_flag_possibly_dirty) {
+		Py_RETURN_NONE;
+	}
 }
 
 static PyObject *dirstate_item_set_untracked(dirstateItemObject *self)
 {
-	if (self->state == 'm') {
-		self->size = dirstate_v1_nonnormal;
-	} else if (self->state == 'n' && self->size == dirstate_v1_from_p2) {
-		self->size = dirstate_v1_from_p2;
-	} else {
-		self->size = 0;
-	}
-	self->state = 'r';
+	self->flags &= ~dirstate_flag_wc_tracked;
 	self->mode = 0;
 	self->mtime = 0;
+	self->size = 0;
 	Py_RETURN_NONE;
 }
 
 static PyMethodDef dirstate_item_methods[] = {
     {"v1_state", (PyCFunction)dirstate_item_v1_state, METH_NOARGS,
      "return a \"state\" suitable for v1 serialization"},
     {"v1_mode", (PyCFunction)dirstate_item_v1_mode, METH_NOARGS,
      "return a \"mode\" suitable for v1 serialization"},
     {"v1_size", (PyCFunction)dirstate_item_v1_size, METH_NOARGS,
      "return a \"size\" suitable for v1 serialization"},
     {"v1_mtime", (PyCFunction)dirstate_item_v1_mtime, METH_NOARGS,
      "return a \"mtime\" suitable for v1 serialization"},
     {"need_delay", (PyCFunction)dirstate_item_need_delay, METH_O,
      "True if the stored mtime would be ambiguous with the current time"},
     {"from_v1_data", (PyCFunction)dirstate_item_from_v1_meth,
      METH_VARARGS | METH_CLASS, "build a new DirstateItem object from V1 data"},
     {"new_added", (PyCFunction)dirstate_item_new_added,
      METH_NOARGS | METH_CLASS,
      "constructor to help legacy API to build a new \"added\" item"},
     {"new_merged", (PyCFunction)dirstate_item_new_merged,
      METH_NOARGS | METH_CLASS,
      "constructor to help legacy API to build a new \"merged\" item"},
     {"new_from_p2", (PyCFunction)dirstate_item_new_from_p2,
      METH_NOARGS | METH_CLASS,
      "constructor to help legacy API to build a new \"from_p2\" item"},
     {"new_possibly_dirty", (PyCFunction)dirstate_item_new_possibly_dirty,
      METH_NOARGS | METH_CLASS,
      "constructor to help legacy API to build a new \"possibly_dirty\" item"},
     {"new_normal", (PyCFunction)dirstate_item_new_normal,
      METH_VARARGS | METH_CLASS,
      "constructor to help legacy API to build a new \"normal\" item"},
     {"set_possibly_dirty", (PyCFunction)dirstate_item_set_possibly_dirty,
      METH_NOARGS, "mark a file as \"possibly dirty\""},
     {"set_untracked", (PyCFunction)dirstate_item_set_untracked, METH_NOARGS,
      "mark a file as \"untracked\""},
     {NULL} /* Sentinel */
 };
 
 static PyObject *dirstate_item_get_mode(dirstateItemObject *self)
 {
 	return PyInt_FromLong(dirstate_item_c_v1_mode(self));
 };
 
 static PyObject *dirstate_item_get_size(dirstateItemObject *self)
 {
 	return PyInt_FromLong(dirstate_item_c_v1_size(self));
 };
 
 static PyObject *dirstate_item_get_mtime(dirstateItemObject *self)
 {
 	return PyInt_FromLong(dirstate_item_c_v1_mtime(self));
 };
 
 static PyObject *dirstate_item_get_state(dirstateItemObject *self)
 {
 	char state = dirstate_item_c_v1_state(self);
 	return PyBytes_FromStringAndSize(&state, 1);
 };
 
 static PyObject *dirstate_item_get_tracked(dirstateItemObject *self)
 {
 	if (dirstate_item_c_tracked(self)) {
 		Py_RETURN_TRUE;
 	} else {
 		Py_RETURN_FALSE;
 	}
 };
 
 static PyObject *dirstate_item_get_added(dirstateItemObject *self)
 {
 	if (dirstate_item_c_added(self)) {
 		Py_RETURN_TRUE;
 	} else {
 		Py_RETURN_FALSE;
 	}
 };
 
 static PyObject *dirstate_item_get_merged(dirstateItemObject *self)
 {
 	if (dirstate_item_c_merged(self)) {
 		Py_RETURN_TRUE;
 	} else {
 		Py_RETURN_FALSE;
 	}
 };
 
 static PyObject *dirstate_item_get_merged_removed(dirstateItemObject *self)
 {
 	if (dirstate_item_c_merged_removed(self)) {
 		Py_RETURN_TRUE;
 	} else {
 		Py_RETURN_FALSE;
 	}
 };
 
 static PyObject *dirstate_item_get_from_p2(dirstateItemObject *self)
 {
 	if (dirstate_item_c_from_p2(self)) {
 		Py_RETURN_TRUE;
 	} else {
 		Py_RETURN_FALSE;
 	}
 };
 
 static PyObject *dirstate_item_get_from_p2_removed(dirstateItemObject *self)
 {
 	if (dirstate_item_c_from_p2_removed(self)) {
 		Py_RETURN_TRUE;
 	} else {
 		Py_RETURN_FALSE;
 	}
 };
 
 static PyObject *dirstate_item_get_removed(dirstateItemObject *self)
 {
 	if (dirstate_item_c_removed(self)) {
 		Py_RETURN_TRUE;
 	} else {
 		Py_RETURN_FALSE;
 	}
 };
 
 static PyObject *dm_nonnormal(dirstateItemObject *self)
 {
 	if ((dirstate_item_c_v1_state(self) != 'n') ||
 	    (dirstate_item_c_v1_mtime(self) == ambiguous_time)) {
 		Py_RETURN_TRUE;
 	} else {
 		Py_RETURN_FALSE;
 	}
 };
 static PyObject *dm_otherparent(dirstateItemObject *self)
 {
 	if (dirstate_item_c_v1_mtime(self) == dirstate_v1_from_p2) {
 		Py_RETURN_TRUE;
 	} else {
 		Py_RETURN_FALSE;
 	}
 };
 
 static PyGetSetDef dirstate_item_getset[] = {
     {"mode", (getter)dirstate_item_get_mode, NULL, "mode", NULL},
     {"size", (getter)dirstate_item_get_size, NULL, "size", NULL},
     {"mtime", (getter)dirstate_item_get_mtime, NULL, "mtime", NULL},
     {"state", (getter)dirstate_item_get_state, NULL, "state", NULL},
     {"tracked", (getter)dirstate_item_get_tracked, NULL, "tracked", NULL},
     {"added", (getter)dirstate_item_get_added, NULL, "added", NULL},
     {"merged_removed", (getter)dirstate_item_get_merged_removed, NULL,
      "merged_removed", NULL},
     {"merged", (getter)dirstate_item_get_merged, NULL, "merged", NULL},
     {"from_p2_removed", (getter)dirstate_item_get_from_p2_removed, NULL,
      "from_p2_removed", NULL},
     {"from_p2", (getter)dirstate_item_get_from_p2, NULL, "from_p2", NULL},
     {"removed", (getter)dirstate_item_get_removed, NULL, "removed", NULL},
     {"dm_nonnormal", (getter)dm_nonnormal, NULL, "dm_nonnormal", NULL},
     {"dm_otherparent", (getter)dm_otherparent, NULL, "dm_otherparent", NULL},
     {NULL} /* Sentinel */
 };
 
 PyTypeObject dirstateItemType = {
     PyVarObject_HEAD_INIT(NULL, 0)     /* header */
     "dirstate_tuple",                  /* tp_name */
     sizeof(dirstateItemObject),        /* tp_basicsize */
     0,                                 /* tp_itemsize */
     (destructor)dirstate_item_dealloc, /* tp_dealloc */
     0,                                 /* tp_print */
     0,                                 /* tp_getattr */
     0,                                 /* tp_setattr */
     0,                                 /* tp_compare */
     0,                                 /* tp_repr */
     0,                                 /* tp_as_number */
     0,                                 /* 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 */
     dirstate_item_methods,             /* tp_methods */
     0,                                 /* tp_members */
     dirstate_item_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_item_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 *)dirstate_item_from_v1_data(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)) {
 		dirstateItemObject *t;
 		if (!dirstate_tuple_check(v)) {
 			PyErr_SetString(PyExc_TypeError,
 			                "expected a dirstate tuple");
 			goto bail;
 		}
 		t = (dirstateItemObject *)v;
 
-		if (t->state == 'n' && t->size == -2) {
+		if (dirstate_item_c_from_p2(t)) {
 			if (PySet_Add(otherpset, fname) == -1) {
 				goto bail;
 			}
 		}
-
-		if (t->state == 'n' && t->mtime != -1) {
-			continue;
-		}
-		if (PySet_Add(nonnset, fname) == -1) {
-			goto bail;
+		if (!(t->flags & dirstate_flag_wc_tracked) ||
+		    !(t->flags &
+		      (dirstate_flag_p1_tracked | dirstate_flag_p2_tracked)) ||
+		    (t->flags &
+		     (dirstate_flag_possibly_dirty | dirstate_flag_merged))) {
+			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);) {
 		dirstateItemObject *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 = (dirstateItemObject *)v;
 
-		state = tuple->state;
-		mode = tuple->mode;
-		size = tuple->size;
-		mtime = tuple->mtime;
+		state = dirstate_item_c_v1_state(tuple);
+		mode = dirstate_item_c_v1_mode(tuple);
+		size = dirstate_item_c_v1_size(tuple);
+		mtime = dirstate_item_c_v1_mtime(tuple);
 		if (state == 'n' && mtime == now) {
 			/* See pure/parsers.py:pack_dirstate for why we do
 			 * this. */
 			mtime = -1;
 			mtime_unset = (PyObject *)dirstate_item_from_v1_data(
 			    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(
 	    dirstate_item_from_v1_data,
 	    "mercurial.cext.parsers.make_dirstate_item_CAPI", NULL);
 	if (capsule != NULL)
 		PyModule_AddObject(mod, "make_dirstate_item_CAPI", capsule);
 
 	if (PyType_Ready(&dirstateItemType) < 0) {
 		return;
 	}
 	Py_INCREF(&dirstateItemType);
 	PyModule_AddObject(mod, "DirstateItem", (PyObject *)&dirstateItemType);
 }
 
 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/cext/util.h

@@ -1,74 +1,83 b''
 /*
  util.h - utility functions for interfacing with the various python APIs.
 
  This software may be used and distributed according to the terms of
  the GNU General Public License, incorporated herein by reference.
 */
 
 #ifndef _HG_UTIL_H_
 #define _HG_UTIL_H_
 
 #include "compat.h"
 
 #if PY_MAJOR_VERSION >= 3
 #define IS_PY3K
 #endif
 
 /* helper to switch things like string literal depending on Python version */
 #ifdef IS_PY3K
 #define PY23(py2, py3) py3
 #else
 #define PY23(py2, py3) py2
 #endif
 
 /* clang-format off */
 typedef struct {
 	PyObject_HEAD
-	char state;
+	char flags;
 	int mode;
 	int size;
 	int mtime;
 } dirstateItemObject;
 /* clang-format on */
 
+static const char dirstate_flag_wc_tracked = 1;
+static const char dirstate_flag_p1_tracked = 1 << 1;
+static const char dirstate_flag_p2_tracked = 1 << 2;
+static const char dirstate_flag_possibly_dirty = 1 << 3;
+static const char dirstate_flag_merged = 1 << 4;
+static const char dirstate_flag_clean_p1 = 1 << 5;
+static const char dirstate_flag_clean_p2 = 1 << 6;
+static const char dirstate_flag_rust_special = 1 << 7;
+
 extern PyTypeObject dirstateItemType;
 #define dirstate_tuple_check(op) (Py_TYPE(op) == &dirstateItemType)
 
 #ifndef MIN
 #define MIN(a, b) (((a) < (b)) ? (a) : (b))
 #endif
 /* VC9 doesn't include bool and lacks stdbool.h based on my searching */
 #if defined(_MSC_VER) || __STDC_VERSION__ < 199901L
 #define true 1
 #define false 0
 typedef unsigned char bool;
 #else
 #include <stdbool.h>
 #endif
 
 static inline PyObject *_dict_new_presized(Py_ssize_t expected_size)
 {
 	/* _PyDict_NewPresized expects a minused parameter, but it actually
 	   creates a dictionary that's the nearest power of two bigger than the
 	   parameter. For example, with the initial minused = 1000, the
 	   dictionary created has size 1024. Of course in a lot of cases that
 	   can be greater than the maximum load factor Python's dict object
 	   expects (= 2/3), so as soon as we cross the threshold we'll resize
 	   anyway. So create a dictionary that's at least 3/2 the size. */
 	return _PyDict_NewPresized(((1 + expected_size) / 2) * 3);
 }
 
 /* Convert a PyInt or PyLong to a long. Returns false if there is an
    error, in which case an exception will already have been set. */
 static inline bool pylong_to_long(PyObject *pylong, long *out)
 {
 	*out = PyLong_AsLong(pylong);
 	/* Fast path to avoid hitting PyErr_Occurred if the value was obviously
 	 * not an error. */
 	if (*out != -1) {
 		return true;
 	}
 	return PyErr_Occurred() == NULL;
 }
 
 #endif /* _HG_UTIL_H_ */