mercurial/parsers.c
author Matt Mackall <mpm@selenic.com>
Fri, 11 May 2012 14:48:24 +0200
changeset 16621 8c3c9031f5aa
parent 16618 6bae941b58ad
parent 16604 48e42f984074
child 16629 1435866c1937
permissions -rw-r--r--
merge with stable
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
6389
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
     1
/*
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
     2
 parsers.c - efficient content parsing
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
     3
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
     4
 Copyright 2008 Matt Mackall <mpm@selenic.com> and others
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
     5
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
     6
 This software may be used and distributed according to the terms of
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
     7
 the GNU General Public License, incorporated herein by reference.
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
     8
*/
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
     9
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
    10
#include <Python.h>
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
    11
#include <ctype.h>
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
    12
#include <string.h>
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
    13
11361
3de3d670d2b6 parsers.c: Added support for py3k.
Renato Cunha <renatoc@gmail.com>
parents: 10449
diff changeset
    14
#include "util.h"
3de3d670d2b6 parsers.c: Added support for py3k.
Renato Cunha <renatoc@gmail.com>
parents: 10449
diff changeset
    15
16617
4fb16743049d parsers: change the type signature of hexdigit
Bryan O'Sullivan <bryano@fb.com>
parents: 16616
diff changeset
    16
static inline int hexdigit(const char *p, Py_ssize_t off)
6389
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
    17
{
16617
4fb16743049d parsers: change the type signature of hexdigit
Bryan O'Sullivan <bryano@fb.com>
parents: 16616
diff changeset
    18
	char c = p[off];
4fb16743049d parsers: change the type signature of hexdigit
Bryan O'Sullivan <bryano@fb.com>
parents: 16616
diff changeset
    19
6389
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
    20
	if (c >= '0' && c <= '9')
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
    21
		return c - '0';
7092
fb3fc27617a2 parsers: speed up hex decoding for manifests
Matt Mackall <mpm@selenic.com>
parents: 7091
diff changeset
    22
	if (c >= 'a' && c <= 'f')
fb3fc27617a2 parsers: speed up hex decoding for manifests
Matt Mackall <mpm@selenic.com>
parents: 7091
diff changeset
    23
		return c - 'a' + 10;
6389
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
    24
	if (c >= 'A' && c <= 'F')
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
    25
		return c - 'A' + 10;
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
    26
7092
fb3fc27617a2 parsers: speed up hex decoding for manifests
Matt Mackall <mpm@selenic.com>
parents: 7091
diff changeset
    27
	PyErr_SetString(PyExc_ValueError, "input contains non-hex character");
fb3fc27617a2 parsers: speed up hex decoding for manifests
Matt Mackall <mpm@selenic.com>
parents: 7091
diff changeset
    28
	return 0;
6389
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
    29
}
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
    30
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
    31
/*
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
    32
 * Turn a hex-encoded string into binary.
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
    33
 */
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
    34
static PyObject *unhexlify(const char *str, int len)
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
    35
{
7092
fb3fc27617a2 parsers: speed up hex decoding for manifests
Matt Mackall <mpm@selenic.com>
parents: 7091
diff changeset
    36
	PyObject *ret;
6395
3f0294536b24 fix const annotation warning
Benoit Boissinot <benoit.boissinot@ens-lyon.org>
parents: 6389
diff changeset
    37
	char *d;
16617
4fb16743049d parsers: change the type signature of hexdigit
Bryan O'Sullivan <bryano@fb.com>
parents: 16616
diff changeset
    38
	int i;
6389
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
    39
11361
3de3d670d2b6 parsers.c: Added support for py3k.
Renato Cunha <renatoc@gmail.com>
parents: 10449
diff changeset
    40
	ret = PyBytes_FromStringAndSize(NULL, len / 2);
3de3d670d2b6 parsers.c: Added support for py3k.
Renato Cunha <renatoc@gmail.com>
parents: 10449
diff changeset
    41
6389
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
    42
	if (!ret)
7092
fb3fc27617a2 parsers: speed up hex decoding for manifests
Matt Mackall <mpm@selenic.com>
parents: 7091
diff changeset
    43
		return NULL;
6389
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
    44
11361
3de3d670d2b6 parsers.c: Added support for py3k.
Renato Cunha <renatoc@gmail.com>
parents: 10449
diff changeset
    45
	d = PyBytes_AsString(ret);
3de3d670d2b6 parsers.c: Added support for py3k.
Renato Cunha <renatoc@gmail.com>
parents: 10449
diff changeset
    46
16617
4fb16743049d parsers: change the type signature of hexdigit
Bryan O'Sullivan <bryano@fb.com>
parents: 16616
diff changeset
    47
	for (i = 0; i < len;) {
4fb16743049d parsers: change the type signature of hexdigit
Bryan O'Sullivan <bryano@fb.com>
parents: 16616
diff changeset
    48
		int hi = hexdigit(str, i++);
4fb16743049d parsers: change the type signature of hexdigit
Bryan O'Sullivan <bryano@fb.com>
parents: 16616
diff changeset
    49
		int lo = hexdigit(str, i++);
6389
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
    50
		*d++ = (hi << 4) | lo;
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
    51
	}
7091
12b35ae03365 parsers: clean up whitespace
Matt Mackall <mpm@selenic.com>
parents: 6395
diff changeset
    52
6389
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
    53
	return ret;
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
    54
}
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
    55
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
    56
/*
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
    57
 * This code assumes that a manifest is stitched together with newline
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
    58
 * ('\n') characters.
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
    59
 */
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
    60
static PyObject *parse_manifest(PyObject *self, PyObject *args)
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
    61
{
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
    62
	PyObject *mfdict, *fdict;
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
    63
	char *str, *cur, *start, *zero;
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
    64
	int len;
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
    65
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
    66
	if (!PyArg_ParseTuple(args, "O!O!s#:parse_manifest",
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
    67
			      &PyDict_Type, &mfdict,
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
    68
			      &PyDict_Type, &fdict,
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
    69
			      &str, &len))
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
    70
		goto quit;
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
    71
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
    72
	for (start = cur = str, zero = NULL; cur < str + len; cur++) {
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
    73
		PyObject *file = NULL, *node = NULL;
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
    74
		PyObject *flags = NULL;
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
    75
		int nlen;
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
    76
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
    77
		if (!*cur) {
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
    78
			zero = cur;
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
    79
			continue;
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
    80
		}
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
    81
		else if (*cur != '\n')
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
    82
			continue;
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
    83
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
    84
		if (!zero) {
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
    85
			PyErr_SetString(PyExc_ValueError,
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
    86
					"manifest entry has no separator");
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
    87
			goto quit;
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
    88
		}
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
    89
11361
3de3d670d2b6 parsers.c: Added support for py3k.
Renato Cunha <renatoc@gmail.com>
parents: 10449
diff changeset
    90
		file = PyBytes_FromStringAndSize(start, zero - start);
3de3d670d2b6 parsers.c: Added support for py3k.
Renato Cunha <renatoc@gmail.com>
parents: 10449
diff changeset
    91
6389
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
    92
		if (!file)
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
    93
			goto bail;
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
    94
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
    95
		nlen = cur - zero - 1;
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
    96
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
    97
		node = unhexlify(zero + 1, nlen > 40 ? 40 : nlen);
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
    98
		if (!node)
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
    99
			goto bail;
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
   100
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
   101
		if (nlen > 40) {
11361
3de3d670d2b6 parsers.c: Added support for py3k.
Renato Cunha <renatoc@gmail.com>
parents: 10449
diff changeset
   102
			flags = PyBytes_FromStringAndSize(zero + 41,
6389
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
   103
							   nlen - 40);
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
   104
			if (!flags)
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
   105
				goto bail;
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
   106
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
   107
			if (PyDict_SetItem(fdict, file, flags) == -1)
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
   108
				goto bail;
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
   109
		}
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
   110
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
   111
		if (PyDict_SetItem(mfdict, file, node) == -1)
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
   112
			goto bail;
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
   113
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
   114
		start = cur + 1;
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
   115
		zero = NULL;
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
   116
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
   117
		Py_XDECREF(flags);
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
   118
		Py_XDECREF(node);
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
   119
		Py_XDECREF(file);
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
   120
		continue;
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
   121
	bail:
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
   122
		Py_XDECREF(flags);
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
   123
		Py_XDECREF(node);
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
   124
		Py_XDECREF(file);
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
   125
		goto quit;
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
   126
	}
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
   127
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
   128
	if (len > 0 && *(cur - 1) != '\n') {
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
   129
		PyErr_SetString(PyExc_ValueError,
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
   130
				"manifest contains trailing garbage");
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
   131
		goto quit;
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
   132
	}
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
   133
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
   134
	Py_INCREF(Py_None);
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
   135
	return Py_None;
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
   136
quit:
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
   137
	return NULL;
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
   138
}
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
   139
7093
16bafcebd3d1 dirstate: C parsing extension
Matt Mackall <mpm@selenic.com>
parents: 7092
diff changeset
   140
static PyObject *parse_dirstate(PyObject *self, PyObject *args)
16bafcebd3d1 dirstate: C parsing extension
Matt Mackall <mpm@selenic.com>
parents: 7092
diff changeset
   141
{
16bafcebd3d1 dirstate: C parsing extension
Matt Mackall <mpm@selenic.com>
parents: 7092
diff changeset
   142
	PyObject *dmap, *cmap, *parents = NULL, *ret = NULL;
16bafcebd3d1 dirstate: C parsing extension
Matt Mackall <mpm@selenic.com>
parents: 7092
diff changeset
   143
	PyObject *fname = NULL, *cname = NULL, *entry = NULL;
16bafcebd3d1 dirstate: C parsing extension
Matt Mackall <mpm@selenic.com>
parents: 7092
diff changeset
   144
	char *str, *cur, *end, *cpos;
7174
4da87407b845 parsers.c: fix integer overflows
Benoit Boissinot <benoit.boissinot@ens-lyon.org>
parents: 7168
diff changeset
   145
	int state, mode, size, mtime;
4da87407b845 parsers.c: fix integer overflows
Benoit Boissinot <benoit.boissinot@ens-lyon.org>
parents: 7168
diff changeset
   146
	unsigned int flen;
7093
16bafcebd3d1 dirstate: C parsing extension
Matt Mackall <mpm@selenic.com>
parents: 7092
diff changeset
   147
	int len;
16bafcebd3d1 dirstate: C parsing extension
Matt Mackall <mpm@selenic.com>
parents: 7092
diff changeset
   148
16bafcebd3d1 dirstate: C parsing extension
Matt Mackall <mpm@selenic.com>
parents: 7092
diff changeset
   149
	if (!PyArg_ParseTuple(args, "O!O!s#:parse_dirstate",
16bafcebd3d1 dirstate: C parsing extension
Matt Mackall <mpm@selenic.com>
parents: 7092
diff changeset
   150
			      &PyDict_Type, &dmap,
16bafcebd3d1 dirstate: C parsing extension
Matt Mackall <mpm@selenic.com>
parents: 7092
diff changeset
   151
			      &PyDict_Type, &cmap,
16bafcebd3d1 dirstate: C parsing extension
Matt Mackall <mpm@selenic.com>
parents: 7092
diff changeset
   152
			      &str, &len))
16bafcebd3d1 dirstate: C parsing extension
Matt Mackall <mpm@selenic.com>
parents: 7092
diff changeset
   153
		goto quit;
16bafcebd3d1 dirstate: C parsing extension
Matt Mackall <mpm@selenic.com>
parents: 7092
diff changeset
   154
16bafcebd3d1 dirstate: C parsing extension
Matt Mackall <mpm@selenic.com>
parents: 7092
diff changeset
   155
	/* read parents */
16bafcebd3d1 dirstate: C parsing extension
Matt Mackall <mpm@selenic.com>
parents: 7092
diff changeset
   156
	if (len < 40)
16bafcebd3d1 dirstate: C parsing extension
Matt Mackall <mpm@selenic.com>
parents: 7092
diff changeset
   157
		goto quit;
16bafcebd3d1 dirstate: C parsing extension
Matt Mackall <mpm@selenic.com>
parents: 7092
diff changeset
   158
16bafcebd3d1 dirstate: C parsing extension
Matt Mackall <mpm@selenic.com>
parents: 7092
diff changeset
   159
	parents = Py_BuildValue("s#s#", str, 20, str + 20, 20);
16bafcebd3d1 dirstate: C parsing extension
Matt Mackall <mpm@selenic.com>
parents: 7092
diff changeset
   160
	if (!parents)
16bafcebd3d1 dirstate: C parsing extension
Matt Mackall <mpm@selenic.com>
parents: 7092
diff changeset
   161
		goto quit;
16bafcebd3d1 dirstate: C parsing extension
Matt Mackall <mpm@selenic.com>
parents: 7092
diff changeset
   162
16bafcebd3d1 dirstate: C parsing extension
Matt Mackall <mpm@selenic.com>
parents: 7092
diff changeset
   163
	/* read filenames */
16bafcebd3d1 dirstate: C parsing extension
Matt Mackall <mpm@selenic.com>
parents: 7092
diff changeset
   164
	cur = str + 40;
16bafcebd3d1 dirstate: C parsing extension
Matt Mackall <mpm@selenic.com>
parents: 7092
diff changeset
   165
	end = str + len;
16bafcebd3d1 dirstate: C parsing extension
Matt Mackall <mpm@selenic.com>
parents: 7092
diff changeset
   166
16bafcebd3d1 dirstate: C parsing extension
Matt Mackall <mpm@selenic.com>
parents: 7092
diff changeset
   167
	while (cur < end - 17) {
16bafcebd3d1 dirstate: C parsing extension
Matt Mackall <mpm@selenic.com>
parents: 7092
diff changeset
   168
		/* unpack header */
16bafcebd3d1 dirstate: C parsing extension
Matt Mackall <mpm@selenic.com>
parents: 7092
diff changeset
   169
		state = *cur;
16437
d126a0d16856 util.h: replace ntohl/htonl with get/putbe32
Matt Mackall <mpm@selenic.com>
parents: 16414
diff changeset
   170
		mode = getbe32(cur + 1);
d126a0d16856 util.h: replace ntohl/htonl with get/putbe32
Matt Mackall <mpm@selenic.com>
parents: 16414
diff changeset
   171
		size = getbe32(cur + 5);
d126a0d16856 util.h: replace ntohl/htonl with get/putbe32
Matt Mackall <mpm@selenic.com>
parents: 16414
diff changeset
   172
		mtime = getbe32(cur + 9);
d126a0d16856 util.h: replace ntohl/htonl with get/putbe32
Matt Mackall <mpm@selenic.com>
parents: 16414
diff changeset
   173
		flen = getbe32(cur + 13);
7093
16bafcebd3d1 dirstate: C parsing extension
Matt Mackall <mpm@selenic.com>
parents: 7092
diff changeset
   174
		cur += 17;
10449
7c8266c1d15a parsers: fix some signed comparison issues
Matt Mackall <mpm@selenic.com>
parents: 10282
diff changeset
   175
		if (cur + flen > end || cur + flen < cur) {
7174
4da87407b845 parsers.c: fix integer overflows
Benoit Boissinot <benoit.boissinot@ens-lyon.org>
parents: 7168
diff changeset
   176
			PyErr_SetString(PyExc_ValueError, "overflow in dirstate");
7093
16bafcebd3d1 dirstate: C parsing extension
Matt Mackall <mpm@selenic.com>
parents: 7092
diff changeset
   177
			goto quit;
7174
4da87407b845 parsers.c: fix integer overflows
Benoit Boissinot <benoit.boissinot@ens-lyon.org>
parents: 7168
diff changeset
   178
		}
7093
16bafcebd3d1 dirstate: C parsing extension
Matt Mackall <mpm@selenic.com>
parents: 7092
diff changeset
   179
16bafcebd3d1 dirstate: C parsing extension
Matt Mackall <mpm@selenic.com>
parents: 7092
diff changeset
   180
		entry = Py_BuildValue("ciii", state, mode, size, mtime);
16bafcebd3d1 dirstate: C parsing extension
Matt Mackall <mpm@selenic.com>
parents: 7092
diff changeset
   181
		if (!entry)
16bafcebd3d1 dirstate: C parsing extension
Matt Mackall <mpm@selenic.com>
parents: 7092
diff changeset
   182
			goto quit;
7175
5d8626b2c1db parsers.c: do not try to untrack after a failure
Benoit Boissinot <benoit.boissinot@ens-lyon.org>
parents: 7174
diff changeset
   183
		PyObject_GC_UnTrack(entry); /* don't waste time with this */
7093
16bafcebd3d1 dirstate: C parsing extension
Matt Mackall <mpm@selenic.com>
parents: 7092
diff changeset
   184
16bafcebd3d1 dirstate: C parsing extension
Matt Mackall <mpm@selenic.com>
parents: 7092
diff changeset
   185
		cpos = memchr(cur, 0, flen);
16bafcebd3d1 dirstate: C parsing extension
Matt Mackall <mpm@selenic.com>
parents: 7092
diff changeset
   186
		if (cpos) {
11361
3de3d670d2b6 parsers.c: Added support for py3k.
Renato Cunha <renatoc@gmail.com>
parents: 10449
diff changeset
   187
			fname = PyBytes_FromStringAndSize(cur, cpos - cur);
3de3d670d2b6 parsers.c: Added support for py3k.
Renato Cunha <renatoc@gmail.com>
parents: 10449
diff changeset
   188
			cname = PyBytes_FromStringAndSize(cpos + 1,
7093
16bafcebd3d1 dirstate: C parsing extension
Matt Mackall <mpm@selenic.com>
parents: 7092
diff changeset
   189
							   flen - (cpos - cur) - 1);
16bafcebd3d1 dirstate: C parsing extension
Matt Mackall <mpm@selenic.com>
parents: 7092
diff changeset
   190
			if (!fname || !cname ||
16bafcebd3d1 dirstate: C parsing extension
Matt Mackall <mpm@selenic.com>
parents: 7092
diff changeset
   191
			    PyDict_SetItem(cmap, fname, cname) == -1 ||
16bafcebd3d1 dirstate: C parsing extension
Matt Mackall <mpm@selenic.com>
parents: 7092
diff changeset
   192
			    PyDict_SetItem(dmap, fname, entry) == -1)
16bafcebd3d1 dirstate: C parsing extension
Matt Mackall <mpm@selenic.com>
parents: 7092
diff changeset
   193
				goto quit;
16bafcebd3d1 dirstate: C parsing extension
Matt Mackall <mpm@selenic.com>
parents: 7092
diff changeset
   194
			Py_DECREF(cname);
16bafcebd3d1 dirstate: C parsing extension
Matt Mackall <mpm@selenic.com>
parents: 7092
diff changeset
   195
		} else {
11361
3de3d670d2b6 parsers.c: Added support for py3k.
Renato Cunha <renatoc@gmail.com>
parents: 10449
diff changeset
   196
			fname = PyBytes_FromStringAndSize(cur, flen);
7093
16bafcebd3d1 dirstate: C parsing extension
Matt Mackall <mpm@selenic.com>
parents: 7092
diff changeset
   197
			if (!fname ||
16bafcebd3d1 dirstate: C parsing extension
Matt Mackall <mpm@selenic.com>
parents: 7092
diff changeset
   198
			    PyDict_SetItem(dmap, fname, entry) == -1)
16bafcebd3d1 dirstate: C parsing extension
Matt Mackall <mpm@selenic.com>
parents: 7092
diff changeset
   199
				goto quit;
16bafcebd3d1 dirstate: C parsing extension
Matt Mackall <mpm@selenic.com>
parents: 7092
diff changeset
   200
		}
16bafcebd3d1 dirstate: C parsing extension
Matt Mackall <mpm@selenic.com>
parents: 7092
diff changeset
   201
		cur += flen;
16bafcebd3d1 dirstate: C parsing extension
Matt Mackall <mpm@selenic.com>
parents: 7092
diff changeset
   202
		Py_DECREF(fname);
16bafcebd3d1 dirstate: C parsing extension
Matt Mackall <mpm@selenic.com>
parents: 7092
diff changeset
   203
		Py_DECREF(entry);
16bafcebd3d1 dirstate: C parsing extension
Matt Mackall <mpm@selenic.com>
parents: 7092
diff changeset
   204
		fname = cname = entry = NULL;
16bafcebd3d1 dirstate: C parsing extension
Matt Mackall <mpm@selenic.com>
parents: 7092
diff changeset
   205
	}
16bafcebd3d1 dirstate: C parsing extension
Matt Mackall <mpm@selenic.com>
parents: 7092
diff changeset
   206
16bafcebd3d1 dirstate: C parsing extension
Matt Mackall <mpm@selenic.com>
parents: 7092
diff changeset
   207
	ret = parents;
16bafcebd3d1 dirstate: C parsing extension
Matt Mackall <mpm@selenic.com>
parents: 7092
diff changeset
   208
	Py_INCREF(ret);
16bafcebd3d1 dirstate: C parsing extension
Matt Mackall <mpm@selenic.com>
parents: 7092
diff changeset
   209
quit:
16bafcebd3d1 dirstate: C parsing extension
Matt Mackall <mpm@selenic.com>
parents: 7092
diff changeset
   210
	Py_XDECREF(fname);
16bafcebd3d1 dirstate: C parsing extension
Matt Mackall <mpm@selenic.com>
parents: 7092
diff changeset
   211
	Py_XDECREF(cname);
16bafcebd3d1 dirstate: C parsing extension
Matt Mackall <mpm@selenic.com>
parents: 7092
diff changeset
   212
	Py_XDECREF(entry);
16bafcebd3d1 dirstate: C parsing extension
Matt Mackall <mpm@selenic.com>
parents: 7092
diff changeset
   213
	Py_XDECREF(parents);
16bafcebd3d1 dirstate: C parsing extension
Matt Mackall <mpm@selenic.com>
parents: 7092
diff changeset
   214
	return ret;
16bafcebd3d1 dirstate: C parsing extension
Matt Mackall <mpm@selenic.com>
parents: 7092
diff changeset
   215
}
16bafcebd3d1 dirstate: C parsing extension
Matt Mackall <mpm@selenic.com>
parents: 7092
diff changeset
   216
16363
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   217
/*
16414
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   218
 * A base-16 trie for fast node->rev mapping.
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   219
 *
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   220
 * Positive value is index of the next node in the trie
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   221
 * Negative value is a leaf: -(rev + 1)
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   222
 * Zero is empty
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   223
 */
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   224
typedef struct {
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   225
	int children[16];
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   226
} nodetree;
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   227
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   228
/*
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   229
 * This class has two behaviours.
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   230
 *
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   231
 * When used in a list-like way (with integer keys), we decode an
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   232
 * entry in a RevlogNG index file on demand. Our last entry is a
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   233
 * sentinel, always a nullid.  We have limited support for
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   234
 * integer-keyed insert and delete, only at elements right before the
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   235
 * sentinel.
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   236
 *
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   237
 * With string keys, we lazily perform a reverse mapping from node to
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   238
 * rev, using a base-16 trie.
16363
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   239
 */
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   240
typedef struct {
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   241
	PyObject_HEAD
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   242
	/* Type-specific fields go here. */
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   243
	PyObject *data;        /* raw bytes of index */
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   244
	PyObject **cache;      /* cached tuples */
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   245
	const char **offsets;  /* populated on demand */
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   246
	Py_ssize_t raw_length; /* original number of elements */
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   247
	Py_ssize_t length;     /* current number of elements */
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   248
	PyObject *added;       /* populated on demand */
16414
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   249
	nodetree *nt;          /* base-16 trie */
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   250
	int ntlength;          /* # nodes in use */
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   251
	int ntcapacity;        /* # nodes allocated */
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   252
	int ntdepth;           /* maximum depth of tree */
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   253
	int ntsplits;          /* # splits performed */
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   254
	int ntrev;             /* last rev scanned */
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   255
	int ntlookups;         /* # lookups */
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   256
	int ntmisses;          /* # lookups that miss the cache */
16363
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   257
	int inlined;
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   258
} indexObject;
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   259
16414
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   260
static Py_ssize_t index_length(const indexObject *self)
16363
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   261
{
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   262
	if (self->added == NULL)
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   263
		return self->length;
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   264
	return self->length + PyList_GET_SIZE(self->added);
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   265
}
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   266
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   267
static PyObject *nullentry;
16414
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   268
static const char nullid[20];
16363
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   269
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   270
static long inline_scan(indexObject *self, const char **offsets);
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   271
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   272
#if LONG_MAX == 0x7fffffffL
16393
ee163a9cf37c util.h: more Python 2.4 fixes
Matt Mackall <mpm@selenic.com>
parents: 16385
diff changeset
   273
static char *tuple_format = "Kiiiiiis#";
16363
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   274
#else
16393
ee163a9cf37c util.h: more Python 2.4 fixes
Matt Mackall <mpm@selenic.com>
parents: 16385
diff changeset
   275
static char *tuple_format = "kiiiiiis#";
16363
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   276
#endif
7108
1ca878d7b849 C implementation of revlog index parsing
Bernhard Leiner <bleiner@gmail.com>
parents: 7093
diff changeset
   277
16414
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   278
/*
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   279
 * Return a pointer to the beginning of a RevlogNG record.
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   280
 */
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   281
static const char *index_deref(indexObject *self, Py_ssize_t pos)
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   282
{
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   283
	if (self->inlined && pos > 0) {
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   284
		if (self->offsets == NULL) {
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   285
			self->offsets = malloc(self->raw_length *
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   286
					       sizeof(*self->offsets));
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   287
			if (self->offsets == NULL)
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   288
				return (const char *)PyErr_NoMemory();
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   289
			inline_scan(self, self->offsets);
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   290
		}
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   291
		return self->offsets[pos];
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   292
	}
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   293
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   294
	return PyString_AS_STRING(self->data) + pos * 64;
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   295
}
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   296
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   297
/*
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   298
 * RevlogNG format (all in big endian, data may be inlined):
7108
1ca878d7b849 C implementation of revlog index parsing
Bernhard Leiner <bleiner@gmail.com>
parents: 7093
diff changeset
   299
 *    6 bytes: offset
1ca878d7b849 C implementation of revlog index parsing
Bernhard Leiner <bleiner@gmail.com>
parents: 7093
diff changeset
   300
 *    2 bytes: flags
1ca878d7b849 C implementation of revlog index parsing
Bernhard Leiner <bleiner@gmail.com>
parents: 7093
diff changeset
   301
 *    4 bytes: compressed length
1ca878d7b849 C implementation of revlog index parsing
Bernhard Leiner <bleiner@gmail.com>
parents: 7093
diff changeset
   302
 *    4 bytes: uncompressed length
1ca878d7b849 C implementation of revlog index parsing
Bernhard Leiner <bleiner@gmail.com>
parents: 7093
diff changeset
   303
 *    4 bytes: base revision
1ca878d7b849 C implementation of revlog index parsing
Bernhard Leiner <bleiner@gmail.com>
parents: 7093
diff changeset
   304
 *    4 bytes: link revision
1ca878d7b849 C implementation of revlog index parsing
Bernhard Leiner <bleiner@gmail.com>
parents: 7093
diff changeset
   305
 *    4 bytes: parent 1 revision
1ca878d7b849 C implementation of revlog index parsing
Bernhard Leiner <bleiner@gmail.com>
parents: 7093
diff changeset
   306
 *    4 bytes: parent 2 revision
1ca878d7b849 C implementation of revlog index parsing
Bernhard Leiner <bleiner@gmail.com>
parents: 7093
diff changeset
   307
 *   32 bytes: nodeid (only 20 bytes used)
1ca878d7b849 C implementation of revlog index parsing
Bernhard Leiner <bleiner@gmail.com>
parents: 7093
diff changeset
   308
 */
16363
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   309
static PyObject *index_get(indexObject *self, Py_ssize_t pos)
7108
1ca878d7b849 C implementation of revlog index parsing
Bernhard Leiner <bleiner@gmail.com>
parents: 7093
diff changeset
   310
{
7154
7fdf7a0a41b7 index parser: fix refcounting in case of errors, refactor
Benoit Boissinot <benoit.boissinot@ens-lyon.org>
parents: 7135
diff changeset
   311
	uint64_t offset_flags;
7108
1ca878d7b849 C implementation of revlog index parsing
Bernhard Leiner <bleiner@gmail.com>
parents: 7093
diff changeset
   312
	int comp_len, uncomp_len, base_rev, link_rev, parent_1, parent_2;
7154
7fdf7a0a41b7 index parser: fix refcounting in case of errors, refactor
Benoit Boissinot <benoit.boissinot@ens-lyon.org>
parents: 7135
diff changeset
   313
	const char *c_node_id;
16363
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   314
	const char *data;
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   315
	Py_ssize_t length = index_length(self);
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   316
	PyObject *entry;
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   317
16414
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   318
	if (pos < 0)
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   319
		pos += length;
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   320
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   321
	if (pos < 0 || pos >= length) {
16363
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   322
		PyErr_SetString(PyExc_IndexError, "revlog index out of range");
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   323
		return NULL;
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   324
	}
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   325
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   326
	if (pos == length - 1) {
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   327
		Py_INCREF(nullentry);
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   328
		return nullentry;
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   329
	}
7108
1ca878d7b849 C implementation of revlog index parsing
Bernhard Leiner <bleiner@gmail.com>
parents: 7093
diff changeset
   330
16363
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   331
	if (pos >= self->length - 1) {
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   332
		PyObject *obj;
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   333
		obj = PyList_GET_ITEM(self->added, pos - self->length + 1);
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   334
		Py_INCREF(obj);
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   335
		return obj;
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   336
	}
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   337
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   338
	if (self->cache) {
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   339
		if (self->cache[pos]) {
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   340
			Py_INCREF(self->cache[pos]);
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   341
			return self->cache[pos];
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   342
		}
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   343
	} else {
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   344
		self->cache = calloc(self->raw_length, sizeof(PyObject *));
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   345
		if (self->cache == NULL)
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   346
			return PyErr_NoMemory();
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   347
	}
7190
aecea6934fdd Some additional space/tab cleanups
Thomas Arendsen Hein <thomas@intevation.de>
parents: 7186
diff changeset
   348
16414
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   349
	data = index_deref(self, pos);
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   350
	if (data == NULL)
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   351
		return NULL;
16363
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   352
16437
d126a0d16856 util.h: replace ntohl/htonl with get/putbe32
Matt Mackall <mpm@selenic.com>
parents: 16414
diff changeset
   353
	offset_flags = getbe32(data + 4);
16363
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   354
	if (pos == 0) /* mask out version number for the first entry */
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   355
		offset_flags &= 0xFFFF;
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   356
	else {
16437
d126a0d16856 util.h: replace ntohl/htonl with get/putbe32
Matt Mackall <mpm@selenic.com>
parents: 16414
diff changeset
   357
		uint32_t offset_high = getbe32(data);
16363
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   358
		offset_flags |= ((uint64_t)offset_high) << 32;
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   359
	}
7154
7fdf7a0a41b7 index parser: fix refcounting in case of errors, refactor
Benoit Boissinot <benoit.boissinot@ens-lyon.org>
parents: 7135
diff changeset
   360
16437
d126a0d16856 util.h: replace ntohl/htonl with get/putbe32
Matt Mackall <mpm@selenic.com>
parents: 16414
diff changeset
   361
	comp_len = getbe32(data + 8);
d126a0d16856 util.h: replace ntohl/htonl with get/putbe32
Matt Mackall <mpm@selenic.com>
parents: 16414
diff changeset
   362
	uncomp_len = getbe32(data + 12);
d126a0d16856 util.h: replace ntohl/htonl with get/putbe32
Matt Mackall <mpm@selenic.com>
parents: 16414
diff changeset
   363
	base_rev = getbe32(data + 16);
d126a0d16856 util.h: replace ntohl/htonl with get/putbe32
Matt Mackall <mpm@selenic.com>
parents: 16414
diff changeset
   364
	link_rev = getbe32(data + 20);
d126a0d16856 util.h: replace ntohl/htonl with get/putbe32
Matt Mackall <mpm@selenic.com>
parents: 16414
diff changeset
   365
	parent_1 = getbe32(data + 24);
d126a0d16856 util.h: replace ntohl/htonl with get/putbe32
Matt Mackall <mpm@selenic.com>
parents: 16414
diff changeset
   366
	parent_2 = getbe32(data + 28);
16363
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   367
	c_node_id = data + 32;
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   368
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   369
	entry = Py_BuildValue(tuple_format, offset_flags, comp_len,
13254
5ef5eb1f3515 revlog: only build the nodemap on demand
Matt Mackall <mpm@selenic.com>
parents: 11361
diff changeset
   370
			      uncomp_len, base_rev, link_rev,
5ef5eb1f3515 revlog: only build the nodemap on demand
Matt Mackall <mpm@selenic.com>
parents: 11361
diff changeset
   371
			      parent_1, parent_2, c_node_id, 20);
5ef5eb1f3515 revlog: only build the nodemap on demand
Matt Mackall <mpm@selenic.com>
parents: 11361
diff changeset
   372
16363
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   373
	if (entry)
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   374
		PyObject_GC_UnTrack(entry);
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   375
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   376
	self->cache[pos] = entry;
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   377
	Py_INCREF(entry);
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   378
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   379
	return entry;
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   380
}
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   381
16414
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   382
/*
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   383
 * Return the 20-byte SHA of the node corresponding to the given rev.
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   384
 */
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   385
static const char *index_node(indexObject *self, Py_ssize_t pos)
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   386
{
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   387
	Py_ssize_t length = index_length(self);
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   388
	const char *data;
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   389
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   390
	if (pos == length - 1)
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   391
		return nullid;
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   392
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   393
	if (pos >= length)
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   394
		return NULL;
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   395
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   396
	if (pos >= self->length - 1) {
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   397
		PyObject *tuple, *str;
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   398
		tuple = PyList_GET_ITEM(self->added, pos - self->length + 1);
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   399
		str = PyTuple_GetItem(tuple, 7);
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   400
		return str ? PyString_AS_STRING(str) : NULL;
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   401
	}
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   402
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   403
	data = index_deref(self, pos);
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   404
	return data ? data + 32 : NULL;
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   405
}
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   406
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   407
static int nt_insert(indexObject *self, const char *node, int rev);
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   408
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   409
static int node_check(PyObject *obj, char **node, Py_ssize_t *nodelen)
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   410
{
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   411
	if (PyString_AsStringAndSize(obj, node, nodelen) == -1)
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   412
		return -1;
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   413
	if (*nodelen == 20)
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   414
		return 0;
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   415
	PyErr_SetString(PyExc_ValueError, "20-byte hash required");
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   416
	return -1;
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   417
}
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   418
16363
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   419
static PyObject *index_insert(indexObject *self, PyObject *args)
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   420
{
16414
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   421
	PyObject *obj;
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   422
	char *node;
16363
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   423
	long offset;
16414
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   424
	Py_ssize_t len, nodelen;
16363
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   425
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   426
	if (!PyArg_ParseTuple(args, "lO", &offset, &obj))
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   427
		return NULL;
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   428
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   429
	if (!PyTuple_Check(obj) || PyTuple_GET_SIZE(obj) != 8) {
16414
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   430
		PyErr_SetString(PyExc_TypeError, "8-tuple required");
16363
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   431
		return NULL;
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   432
	}
7108
1ca878d7b849 C implementation of revlog index parsing
Bernhard Leiner <bleiner@gmail.com>
parents: 7093
diff changeset
   433
16414
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   434
	if (node_check(PyTuple_GET_ITEM(obj, 7), &node, &nodelen) == -1)
16363
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   435
		return NULL;
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   436
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   437
	len = index_length(self);
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   438
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   439
	if (offset < 0)
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   440
		offset += len;
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   441
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   442
	if (offset != len - 1) {
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   443
		PyErr_SetString(PyExc_IndexError,
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   444
				"insert only supported at index -1");
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   445
		return NULL;
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   446
	}
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   447
16414
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   448
	if (offset > INT_MAX) {
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   449
		PyErr_SetString(PyExc_ValueError,
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   450
				"currently only 2**31 revs supported");
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   451
		return NULL;
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   452
	}
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   453
16363
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   454
	if (self->added == NULL) {
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   455
		self->added = PyList_New(0);
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   456
		if (self->added == NULL)
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   457
			return NULL;
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   458
	}
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   459
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   460
	if (PyList_Append(self->added, obj) == -1)
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   461
		return NULL;
13254
5ef5eb1f3515 revlog: only build the nodemap on demand
Matt Mackall <mpm@selenic.com>
parents: 11361
diff changeset
   462
16414
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   463
	if (self->nt)
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   464
		nt_insert(self, node, (int)offset);
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   465
16363
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   466
	Py_RETURN_NONE;
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   467
}
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   468
16370
28bb4daf070c parsers: fix a memleak, and add a clearcaches method to the index
Bryan O'Sullivan <bryano@fb.com>
parents: 16363
diff changeset
   469
static void _index_clearcaches(indexObject *self)
28bb4daf070c parsers: fix a memleak, and add a clearcaches method to the index
Bryan O'Sullivan <bryano@fb.com>
parents: 16363
diff changeset
   470
{
28bb4daf070c parsers: fix a memleak, and add a clearcaches method to the index
Bryan O'Sullivan <bryano@fb.com>
parents: 16363
diff changeset
   471
	if (self->cache) {
28bb4daf070c parsers: fix a memleak, and add a clearcaches method to the index
Bryan O'Sullivan <bryano@fb.com>
parents: 16363
diff changeset
   472
		Py_ssize_t i;
28bb4daf070c parsers: fix a memleak, and add a clearcaches method to the index
Bryan O'Sullivan <bryano@fb.com>
parents: 16363
diff changeset
   473
28bb4daf070c parsers: fix a memleak, and add a clearcaches method to the index
Bryan O'Sullivan <bryano@fb.com>
parents: 16363
diff changeset
   474
		for (i = 0; i < self->raw_length; i++) {
16572
8d44b5a2974f parsers: fix refcount leak, simplify init of index (issue3417)
Bryan O'Sullivan <bryano@fb.com>
parents: 16437
diff changeset
   475
			if (self->cache[i]) {
8d44b5a2974f parsers: fix refcount leak, simplify init of index (issue3417)
Bryan O'Sullivan <bryano@fb.com>
parents: 16437
diff changeset
   476
				Py_DECREF(self->cache[i]);
8d44b5a2974f parsers: fix refcount leak, simplify init of index (issue3417)
Bryan O'Sullivan <bryano@fb.com>
parents: 16437
diff changeset
   477
				self->cache[i] = NULL;
8d44b5a2974f parsers: fix refcount leak, simplify init of index (issue3417)
Bryan O'Sullivan <bryano@fb.com>
parents: 16437
diff changeset
   478
			}
16370
28bb4daf070c parsers: fix a memleak, and add a clearcaches method to the index
Bryan O'Sullivan <bryano@fb.com>
parents: 16363
diff changeset
   479
		}
28bb4daf070c parsers: fix a memleak, and add a clearcaches method to the index
Bryan O'Sullivan <bryano@fb.com>
parents: 16363
diff changeset
   480
		free(self->cache);
28bb4daf070c parsers: fix a memleak, and add a clearcaches method to the index
Bryan O'Sullivan <bryano@fb.com>
parents: 16363
diff changeset
   481
		self->cache = NULL;
28bb4daf070c parsers: fix a memleak, and add a clearcaches method to the index
Bryan O'Sullivan <bryano@fb.com>
parents: 16363
diff changeset
   482
	}
28bb4daf070c parsers: fix a memleak, and add a clearcaches method to the index
Bryan O'Sullivan <bryano@fb.com>
parents: 16363
diff changeset
   483
	if (self->offsets) {
28bb4daf070c parsers: fix a memleak, and add a clearcaches method to the index
Bryan O'Sullivan <bryano@fb.com>
parents: 16363
diff changeset
   484
		free(self->offsets);
28bb4daf070c parsers: fix a memleak, and add a clearcaches method to the index
Bryan O'Sullivan <bryano@fb.com>
parents: 16363
diff changeset
   485
		self->offsets = NULL;
28bb4daf070c parsers: fix a memleak, and add a clearcaches method to the index
Bryan O'Sullivan <bryano@fb.com>
parents: 16363
diff changeset
   486
	}
16414
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   487
	if (self->nt) {
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   488
		free(self->nt);
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   489
		self->nt = NULL;
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   490
	}
16370
28bb4daf070c parsers: fix a memleak, and add a clearcaches method to the index
Bryan O'Sullivan <bryano@fb.com>
parents: 16363
diff changeset
   491
}
28bb4daf070c parsers: fix a memleak, and add a clearcaches method to the index
Bryan O'Sullivan <bryano@fb.com>
parents: 16363
diff changeset
   492
28bb4daf070c parsers: fix a memleak, and add a clearcaches method to the index
Bryan O'Sullivan <bryano@fb.com>
parents: 16363
diff changeset
   493
static PyObject *index_clearcaches(indexObject *self)
28bb4daf070c parsers: fix a memleak, and add a clearcaches method to the index
Bryan O'Sullivan <bryano@fb.com>
parents: 16363
diff changeset
   494
{
28bb4daf070c parsers: fix a memleak, and add a clearcaches method to the index
Bryan O'Sullivan <bryano@fb.com>
parents: 16363
diff changeset
   495
	_index_clearcaches(self);
16414
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   496
	self->ntlength = self->ntcapacity = 0;
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   497
	self->ntdepth = self->ntsplits = 0;
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   498
	self->ntrev = -1;
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   499
	self->ntlookups = self->ntmisses = 0;
16370
28bb4daf070c parsers: fix a memleak, and add a clearcaches method to the index
Bryan O'Sullivan <bryano@fb.com>
parents: 16363
diff changeset
   500
	Py_RETURN_NONE;
28bb4daf070c parsers: fix a memleak, and add a clearcaches method to the index
Bryan O'Sullivan <bryano@fb.com>
parents: 16363
diff changeset
   501
}
28bb4daf070c parsers: fix a memleak, and add a clearcaches method to the index
Bryan O'Sullivan <bryano@fb.com>
parents: 16363
diff changeset
   502
16414
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   503
static PyObject *index_stats(indexObject *self)
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   504
{
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   505
	PyObject *obj = PyDict_New();
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   506
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   507
	if (obj == NULL)
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   508
		return NULL;
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   509
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   510
#define istat(__n, __d) \
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   511
	if (PyDict_SetItemString(obj, __d, PyInt_FromLong(self->__n)) == -1) \
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   512
		goto bail;
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   513
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   514
	if (self->added) {
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   515
		Py_ssize_t len = PyList_GET_SIZE(self->added);
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   516
		if (PyDict_SetItemString(obj, "index entries added",
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   517
					 PyInt_FromLong(len)) == -1)
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   518
			goto bail;
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   519
	}
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   520
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   521
	if (self->raw_length != self->length - 1)
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   522
		istat(raw_length, "revs on disk");
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   523
	istat(length, "revs in memory");
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   524
	istat(ntcapacity, "node trie capacity");
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   525
	istat(ntdepth, "node trie depth");
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   526
	istat(ntlength, "node trie count");
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   527
	istat(ntlookups, "node trie lookups");
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   528
	istat(ntmisses, "node trie misses");
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   529
	istat(ntrev, "node trie last rev scanned");
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   530
	istat(ntsplits, "node trie splits");
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   531
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   532
#undef istat
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   533
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   534
	return obj;
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   535
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   536
bail:
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   537
	Py_XDECREF(obj);
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   538
	return NULL;
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   539
}
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   540
16618
6bae941b58ad parsers: change the type of nt_level
Bryan O'Sullivan <bryano@fb.com>
parents: 16617
diff changeset
   541
static inline int nt_level(const char *node, Py_ssize_t level)
16414
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   542
{
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   543
	int v = node[level>>1];
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   544
	if (!(level & 1))
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   545
		v >>= 4;
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   546
	return v & 0xf;
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   547
}
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   548
16616
8f79aabd96f6 parsers: allow nt_find to signal an ambiguous match
Bryan O'Sullivan <bryano@fb.com>
parents: 16615
diff changeset
   549
/*
8f79aabd96f6 parsers: allow nt_find to signal an ambiguous match
Bryan O'Sullivan <bryano@fb.com>
parents: 16615
diff changeset
   550
 * Return values:
8f79aabd96f6 parsers: allow nt_find to signal an ambiguous match
Bryan O'Sullivan <bryano@fb.com>
parents: 16615
diff changeset
   551
 *
8f79aabd96f6 parsers: allow nt_find to signal an ambiguous match
Bryan O'Sullivan <bryano@fb.com>
parents: 16615
diff changeset
   552
 *   -4: match is ambiguous (multiple candidates)
8f79aabd96f6 parsers: allow nt_find to signal an ambiguous match
Bryan O'Sullivan <bryano@fb.com>
parents: 16615
diff changeset
   553
 *   -2: not found
8f79aabd96f6 parsers: allow nt_find to signal an ambiguous match
Bryan O'Sullivan <bryano@fb.com>
parents: 16615
diff changeset
   554
 * rest: valid rev
8f79aabd96f6 parsers: allow nt_find to signal an ambiguous match
Bryan O'Sullivan <bryano@fb.com>
parents: 16615
diff changeset
   555
 */
16414
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   556
static int nt_find(indexObject *self, const char *node, Py_ssize_t nodelen)
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   557
{
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   558
	int level, off;
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   559
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   560
	if (nodelen == 20 && node[0] == '\0' && memcmp(node, nullid, 20) == 0)
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   561
		return -1;
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   562
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   563
	if (self->nt == NULL)
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   564
		return -2;
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   565
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   566
	for (level = off = 0; level < nodelen; level++) {
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   567
		int k = nt_level(node, level);
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   568
		nodetree *n = &self->nt[off];
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   569
		int v = n->children[k];
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   570
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   571
		if (v < 0) {
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   572
			const char *n;
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   573
			v = -v - 1;
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   574
			n = index_node(self, v);
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   575
			if (n == NULL)
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   576
				return -2;
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   577
			return memcmp(node, n, nodelen > 20 ? 20 : nodelen)
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   578
				? -2 : v;
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   579
		}
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   580
		if (v == 0)
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   581
			return -2;
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   582
		off = v;
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   583
	}
16616
8f79aabd96f6 parsers: allow nt_find to signal an ambiguous match
Bryan O'Sullivan <bryano@fb.com>
parents: 16615
diff changeset
   584
	/* multiple matches against an ambiguous prefix */
8f79aabd96f6 parsers: allow nt_find to signal an ambiguous match
Bryan O'Sullivan <bryano@fb.com>
parents: 16615
diff changeset
   585
	return -4;
16414
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   586
}
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   587
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   588
static int nt_new(indexObject *self)
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   589
{
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   590
	if (self->ntlength == self->ntcapacity) {
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   591
		self->ntcapacity *= 2;
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   592
		self->nt = realloc(self->nt,
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   593
				   self->ntcapacity * sizeof(nodetree));
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   594
		if (self->nt == NULL) {
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   595
			PyErr_SetString(PyExc_MemoryError, "out of memory");
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   596
			return -1;
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   597
		}
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   598
		memset(&self->nt[self->ntlength], 0,
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   599
		       sizeof(nodetree) * (self->ntcapacity - self->ntlength));
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   600
	}
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   601
	return self->ntlength++;
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   602
}
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   603
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   604
static int nt_insert(indexObject *self, const char *node, int rev)
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   605
{
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   606
	int level = 0;
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   607
	int off = 0;
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   608
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   609
	while (level < 20) {
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   610
		int k = nt_level(node, level);
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   611
		nodetree *n;
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   612
		int v;
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   613
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   614
		n = &self->nt[off];
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   615
		v = n->children[k];
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   616
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   617
		if (v == 0) {
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   618
			n->children[k] = -rev - 1;
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   619
			return 0;
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   620
		}
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   621
		if (v < 0) {
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   622
			const char *oldnode = index_node(self, -v - 1);
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   623
			int noff;
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   624
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   625
			if (!oldnode || !memcmp(oldnode, node, 20)) {
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   626
				n->children[k] = -rev - 1;
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   627
				return 0;
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   628
			}
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   629
			noff = nt_new(self);
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   630
			if (noff == -1)
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   631
				return -1;
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   632
			/* self->nt may have been changed by realloc */
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   633
			self->nt[off].children[k] = noff;
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   634
			off = noff;
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   635
			n = &self->nt[off];
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   636
			n->children[nt_level(oldnode, ++level)] = v;
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   637
			if (level > self->ntdepth)
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   638
				self->ntdepth = level;
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   639
			self->ntsplits += 1;
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   640
		} else {
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   641
			level += 1;
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   642
			off = v;
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   643
		}
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   644
	}
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   645
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   646
	return -1;
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   647
}
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   648
16615
96fa9dd1db38 parsers: factor out radix tree initialization
Bryan O'Sullivan <bryano@fb.com>
parents: 16614
diff changeset
   649
static int nt_init(indexObject *self)
96fa9dd1db38 parsers: factor out radix tree initialization
Bryan O'Sullivan <bryano@fb.com>
parents: 16614
diff changeset
   650
{
96fa9dd1db38 parsers: factor out radix tree initialization
Bryan O'Sullivan <bryano@fb.com>
parents: 16614
diff changeset
   651
	if (self->nt == NULL) {
96fa9dd1db38 parsers: factor out radix tree initialization
Bryan O'Sullivan <bryano@fb.com>
parents: 16614
diff changeset
   652
		self->ntcapacity = self->raw_length < 4
96fa9dd1db38 parsers: factor out radix tree initialization
Bryan O'Sullivan <bryano@fb.com>
parents: 16614
diff changeset
   653
			? 4 : self->raw_length / 2;
96fa9dd1db38 parsers: factor out radix tree initialization
Bryan O'Sullivan <bryano@fb.com>
parents: 16614
diff changeset
   654
		self->nt = calloc(self->ntcapacity, sizeof(nodetree));
96fa9dd1db38 parsers: factor out radix tree initialization
Bryan O'Sullivan <bryano@fb.com>
parents: 16614
diff changeset
   655
		if (self->nt == NULL) {
96fa9dd1db38 parsers: factor out radix tree initialization
Bryan O'Sullivan <bryano@fb.com>
parents: 16614
diff changeset
   656
			PyErr_NoMemory();
96fa9dd1db38 parsers: factor out radix tree initialization
Bryan O'Sullivan <bryano@fb.com>
parents: 16614
diff changeset
   657
			return -1;
96fa9dd1db38 parsers: factor out radix tree initialization
Bryan O'Sullivan <bryano@fb.com>
parents: 16614
diff changeset
   658
		}
96fa9dd1db38 parsers: factor out radix tree initialization
Bryan O'Sullivan <bryano@fb.com>
parents: 16614
diff changeset
   659
		self->ntlength = 1;
96fa9dd1db38 parsers: factor out radix tree initialization
Bryan O'Sullivan <bryano@fb.com>
parents: 16614
diff changeset
   660
		self->ntrev = (int)index_length(self) - 1;
96fa9dd1db38 parsers: factor out radix tree initialization
Bryan O'Sullivan <bryano@fb.com>
parents: 16614
diff changeset
   661
		self->ntlookups = 1;
96fa9dd1db38 parsers: factor out radix tree initialization
Bryan O'Sullivan <bryano@fb.com>
parents: 16614
diff changeset
   662
		self->ntmisses = 0;
96fa9dd1db38 parsers: factor out radix tree initialization
Bryan O'Sullivan <bryano@fb.com>
parents: 16614
diff changeset
   663
	}
96fa9dd1db38 parsers: factor out radix tree initialization
Bryan O'Sullivan <bryano@fb.com>
parents: 16614
diff changeset
   664
	return 0;
96fa9dd1db38 parsers: factor out radix tree initialization
Bryan O'Sullivan <bryano@fb.com>
parents: 16614
diff changeset
   665
}
96fa9dd1db38 parsers: factor out radix tree initialization
Bryan O'Sullivan <bryano@fb.com>
parents: 16614
diff changeset
   666
16414
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   667
/*
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   668
 * Return values:
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   669
 *
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   670
 *   -3: error (exception set)
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   671
 *   -2: not found (no exception set)
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   672
 * rest: valid rev
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   673
 */
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   674
static int index_find_node(indexObject *self,
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   675
			   const char *node, Py_ssize_t nodelen)
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   676
{
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   677
	int rev;
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   678
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   679
	self->ntlookups++;
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   680
	rev = nt_find(self, node, nodelen);
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   681
	if (rev >= -1)
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   682
		return rev;
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   683
16615
96fa9dd1db38 parsers: factor out radix tree initialization
Bryan O'Sullivan <bryano@fb.com>
parents: 16614
diff changeset
   684
	if (nt_init(self) == -1)
96fa9dd1db38 parsers: factor out radix tree initialization
Bryan O'Sullivan <bryano@fb.com>
parents: 16614
diff changeset
   685
		return -3;
16414
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   686
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   687
	/*
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   688
	 * For the first handful of lookups, we scan the entire index,
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   689
	 * and cache only the matching nodes. This optimizes for cases
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   690
	 * like "hg tip", where only a few nodes are accessed.
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   691
	 *
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   692
	 * After that, we cache every node we visit, using a single
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   693
	 * scan amortized over multiple lookups.  This gives the best
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   694
	 * bulk performance, e.g. for "hg log".
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   695
	 */
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   696
	if (self->ntmisses++ < 4) {
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   697
		for (rev = self->ntrev - 1; rev >= 0; rev--) {
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   698
			const char *n = index_node(self, rev);
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   699
			if (n == NULL)
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   700
				return -2;
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   701
			if (memcmp(node, n, nodelen > 20 ? 20 : nodelen) == 0) {
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   702
				if (nt_insert(self, n, rev) == -1)
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   703
					return -3;
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   704
				break;
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   705
			}
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   706
		}
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   707
	} else {
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   708
		for (rev = self->ntrev - 1; rev >= 0; rev--) {
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   709
			const char *n = index_node(self, rev);
16614
1d800eb9ba52 parsers: update ntrev when we stop scanning
Bryan O'Sullivan <bryano@fb.com>
parents: 16597
diff changeset
   710
			if (n == NULL) {
1d800eb9ba52 parsers: update ntrev when we stop scanning
Bryan O'Sullivan <bryano@fb.com>
parents: 16597
diff changeset
   711
				self->ntrev = rev + 1;
16414
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   712
				return -2;
16614
1d800eb9ba52 parsers: update ntrev when we stop scanning
Bryan O'Sullivan <bryano@fb.com>
parents: 16597
diff changeset
   713
			}
1d800eb9ba52 parsers: update ntrev when we stop scanning
Bryan O'Sullivan <bryano@fb.com>
parents: 16597
diff changeset
   714
			if (nt_insert(self, n, rev) == -1) {
1d800eb9ba52 parsers: update ntrev when we stop scanning
Bryan O'Sullivan <bryano@fb.com>
parents: 16597
diff changeset
   715
				self->ntrev = rev + 1;
16414
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   716
				return -3;
16614
1d800eb9ba52 parsers: update ntrev when we stop scanning
Bryan O'Sullivan <bryano@fb.com>
parents: 16597
diff changeset
   717
			}
16414
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   718
			if (memcmp(node, n, nodelen > 20 ? 20 : nodelen) == 0) {
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   719
				break;
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   720
			}
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   721
		}
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   722
		self->ntrev = rev;
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   723
	}
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   724
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   725
	if (rev >= 0)
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   726
		return rev;
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   727
	return -2;
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   728
}
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   729
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   730
static PyObject *raise_revlog_error(void)
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   731
{
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   732
	static PyObject *errclass;
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   733
	PyObject *mod = NULL, *errobj;
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   734
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   735
	if (errclass == NULL) {
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   736
		PyObject *dict;
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   737
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   738
		mod = PyImport_ImportModule("mercurial.error");
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   739
		if (mod == NULL)
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   740
			goto classfail;
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   741
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   742
		dict = PyModule_GetDict(mod);
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   743
		if (dict == NULL)
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   744
			goto classfail;
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   745
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   746
		errclass = PyDict_GetItemString(dict, "RevlogError");
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   747
		if (errclass == NULL) {
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   748
			PyErr_SetString(PyExc_SystemError,
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   749
					"could not find RevlogError");
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   750
			goto classfail;
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   751
		}
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   752
		Py_INCREF(errclass);
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   753
	}
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   754
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   755
	errobj = PyObject_CallFunction(errclass, NULL);
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   756
	if (errobj == NULL)
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   757
		return NULL;
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   758
	PyErr_SetObject(errclass, errobj);
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   759
	return errobj;
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   760
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   761
classfail:
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   762
	Py_XDECREF(mod);
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   763
	return NULL;
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   764
}
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   765
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   766
static PyObject *index_getitem(indexObject *self, PyObject *value)
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   767
{
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   768
	char *node;
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   769
	Py_ssize_t nodelen;
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   770
	int rev;
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   771
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   772
	if (PyInt_Check(value))
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   773
		return index_get(self, PyInt_AS_LONG(value));
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   774
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   775
	if (PyString_AsStringAndSize(value, &node, &nodelen) == -1)
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   776
		return NULL;
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   777
	rev = index_find_node(self, node, nodelen);
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   778
	if (rev >= -1)
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   779
		return PyInt_FromLong(rev);
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   780
	if (rev == -2)
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   781
		raise_revlog_error();
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   782
	return NULL;
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   783
}
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   784
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   785
static PyObject *index_m_get(indexObject *self, PyObject *args)
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   786
{
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   787
	char *node;
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   788
	int nodelen, rev;
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   789
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   790
	if (!PyArg_ParseTuple(args, "s#", &node, &nodelen))
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   791
		return NULL;
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   792
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   793
	rev = index_find_node(self, node, nodelen);
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   794
	if (rev ==  -3)
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   795
		return NULL;
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   796
	if (rev == -2)
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   797
		Py_RETURN_NONE;
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   798
	return PyInt_FromLong(rev);
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   799
}
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   800
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   801
static int index_contains(indexObject *self, PyObject *value)
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   802
{
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   803
	char *node;
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   804
	Py_ssize_t nodelen;
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   805
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   806
	if (PyInt_Check(value)) {
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   807
		long rev = PyInt_AS_LONG(value);
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   808
		return rev >= -1 && rev < index_length(self);
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   809
	}
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   810
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   811
	if (!PyString_Check(value))
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   812
		return 0;
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   813
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   814
	node = PyString_AS_STRING(value);
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   815
	nodelen = PyString_GET_SIZE(value);
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   816
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   817
	switch (index_find_node(self, node, nodelen)) {
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   818
	case -3:
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   819
		return -1;
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   820
	case -2:
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   821
		return 0;
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   822
	default:
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   823
		return 1;
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   824
	}
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   825
}
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   826
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   827
/*
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   828
 * Invalidate any trie entries introduced by added revs.
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   829
 */
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   830
static void nt_invalidate_added(indexObject *self, Py_ssize_t start)
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   831
{
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   832
	Py_ssize_t i, len = PyList_GET_SIZE(self->added);
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   833
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   834
	for (i = start; i < len; i++) {
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   835
		PyObject *tuple = PyList_GET_ITEM(self->added, i);
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   836
		PyObject *node = PyTuple_GET_ITEM(tuple, 7);
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   837
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   838
		nt_insert(self, PyString_AS_STRING(node), -1);
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   839
	}
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   840
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   841
	if (start == 0) {
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   842
		Py_DECREF(self->added);
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   843
		self->added = NULL;
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   844
	}
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   845
}
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   846
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   847
/*
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   848
 * Delete a numeric range of revs, which must be at the end of the
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   849
 * range, but exclude the sentinel nullid entry.
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   850
 */
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   851
static int index_slice_del(indexObject *self, PyObject *item)
16363
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   852
{
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   853
	Py_ssize_t start, stop, step, slicelength;
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   854
	Py_ssize_t length = index_length(self);
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   855
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   856
	if (PySlice_GetIndicesEx((PySliceObject*)item, length,
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   857
				 &start, &stop, &step, &slicelength) < 0)
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   858
		return -1;
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   859
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   860
	if (slicelength <= 0)
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   861
		return 0;
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   862
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   863
	if ((step < 0 && start < stop) || (step > 0 && start > stop))
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   864
		stop = start;
7108
1ca878d7b849 C implementation of revlog index parsing
Bernhard Leiner <bleiner@gmail.com>
parents: 7093
diff changeset
   865
16363
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   866
	if (step < 0) {
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   867
		stop = start + 1;
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   868
		start = stop + step*(slicelength - 1) - 1;
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   869
		step = -step;
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   870
	}
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   871
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   872
	if (step != 1) {
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   873
		PyErr_SetString(PyExc_ValueError,
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   874
				"revlog index delete requires step size of 1");
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   875
		return -1;
7108
1ca878d7b849 C implementation of revlog index parsing
Bernhard Leiner <bleiner@gmail.com>
parents: 7093
diff changeset
   876
	}
16363
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   877
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   878
	if (stop != length - 1) {
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   879
		PyErr_SetString(PyExc_IndexError,
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   880
				"revlog index deletion indices are invalid");
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   881
		return -1;
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   882
	}
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   883
16414
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   884
	if (start < self->length - 1) {
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   885
		if (self->nt) {
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   886
			Py_ssize_t i;
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   887
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   888
			for (i = start + 1; i < self->length - 1; i++) {
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   889
				const char *node = index_node(self, i);
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   890
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   891
				if (node)
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   892
					nt_insert(self, node, -1);
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   893
			}
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   894
			if (self->added)
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   895
				nt_invalidate_added(self, 0);
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   896
			if (self->ntrev > start)
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   897
				self->ntrev = (int)start;
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   898
		}
16363
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   899
		self->length = start + 1;
7154
7fdf7a0a41b7 index parser: fix refcounting in case of errors, refactor
Benoit Boissinot <benoit.boissinot@ens-lyon.org>
parents: 7135
diff changeset
   900
		return 0;
7108
1ca878d7b849 C implementation of revlog index parsing
Bernhard Leiner <bleiner@gmail.com>
parents: 7093
diff changeset
   901
	}
1ca878d7b849 C implementation of revlog index parsing
Bernhard Leiner <bleiner@gmail.com>
parents: 7093
diff changeset
   902
16414
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   903
	if (self->nt) {
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   904
		nt_invalidate_added(self, start - self->length + 1);
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   905
		if (self->ntrev > start)
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   906
			self->ntrev = (int)start;
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   907
	}
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   908
	return self->added
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   909
		? PyList_SetSlice(self->added, start - self->length + 1,
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   910
				  PyList_GET_SIZE(self->added), NULL)
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   911
		: 0;
16363
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   912
}
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   913
16414
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   914
/*
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   915
 * Supported ops:
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   916
 *
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   917
 * slice deletion
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   918
 * string assignment (extend node->rev mapping)
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   919
 * string deletion (shrink node->rev mapping)
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   920
 */
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   921
static int index_assign_subscript(indexObject *self, PyObject *item,
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   922
				  PyObject *value)
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   923
{
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   924
	char *node;
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   925
	Py_ssize_t nodelen;
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   926
	long rev;
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   927
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   928
	if (PySlice_Check(item) && value == NULL)
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   929
		return index_slice_del(self, item);
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   930
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   931
	if (node_check(item, &node, &nodelen) == -1)
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   932
		return -1;
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   933
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   934
	if (value == NULL)
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   935
		return self->nt ? nt_insert(self, node, -1) : 0;
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   936
	rev = PyInt_AsLong(value);
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   937
	if (rev > INT_MAX || rev < 0) {
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   938
		if (!PyErr_Occurred())
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   939
			PyErr_SetString(PyExc_ValueError, "rev out of range");
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   940
		return -1;
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   941
	}
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   942
	return nt_insert(self, node, (int)rev);
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   943
}
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   944
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   945
/*
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   946
 * Find all RevlogNG entries in an index that has inline data. Update
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   947
 * the optional "offsets" table with those entries.
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
   948
 */
16363
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   949
static long inline_scan(indexObject *self, const char **offsets)
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   950
{
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   951
	const char *data = PyString_AS_STRING(self->data);
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   952
	const char *end = data + PyString_GET_SIZE(self->data);
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   953
	const long hdrsize = 64;
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   954
	long incr = hdrsize;
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   955
	Py_ssize_t len = 0;
13254
5ef5eb1f3515 revlog: only build the nodemap on demand
Matt Mackall <mpm@selenic.com>
parents: 11361
diff changeset
   956
16363
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   957
	while (data + hdrsize <= end) {
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   958
		uint32_t comp_len;
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   959
		const char *old_data;
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   960
		/* 3rd element of header is length of compressed inline data */
16437
d126a0d16856 util.h: replace ntohl/htonl with get/putbe32
Matt Mackall <mpm@selenic.com>
parents: 16414
diff changeset
   961
		comp_len = getbe32(data + 8);
d126a0d16856 util.h: replace ntohl/htonl with get/putbe32
Matt Mackall <mpm@selenic.com>
parents: 16414
diff changeset
   962
		incr = hdrsize + comp_len;
16363
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   963
		if (incr < hdrsize)
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   964
			break;
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   965
		if (offsets)
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   966
			offsets[len] = data;
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   967
		len++;
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   968
		old_data = data;
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   969
		data += incr;
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   970
		if (data <= old_data)
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   971
			break;
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   972
	}
13254
5ef5eb1f3515 revlog: only build the nodemap on demand
Matt Mackall <mpm@selenic.com>
parents: 11361
diff changeset
   973
16363
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   974
	if (data != end && data + hdrsize != end) {
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   975
		if (!PyErr_Occurred())
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   976
			PyErr_SetString(PyExc_ValueError, "corrupt index file");
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   977
		return -1;
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   978
	}
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   979
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   980
	return len;
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   981
}
13254
5ef5eb1f3515 revlog: only build the nodemap on demand
Matt Mackall <mpm@selenic.com>
parents: 11361
diff changeset
   982
16572
8d44b5a2974f parsers: fix refcount leak, simplify init of index (issue3417)
Bryan O'Sullivan <bryano@fb.com>
parents: 16437
diff changeset
   983
static int index_init(indexObject *self, PyObject *args)
16363
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   984
{
16572
8d44b5a2974f parsers: fix refcount leak, simplify init of index (issue3417)
Bryan O'Sullivan <bryano@fb.com>
parents: 16437
diff changeset
   985
	PyObject *data_obj, *inlined_obj;
8d44b5a2974f parsers: fix refcount leak, simplify init of index (issue3417)
Bryan O'Sullivan <bryano@fb.com>
parents: 16437
diff changeset
   986
	Py_ssize_t size;
8d44b5a2974f parsers: fix refcount leak, simplify init of index (issue3417)
Bryan O'Sullivan <bryano@fb.com>
parents: 16437
diff changeset
   987
8d44b5a2974f parsers: fix refcount leak, simplify init of index (issue3417)
Bryan O'Sullivan <bryano@fb.com>
parents: 16437
diff changeset
   988
	if (!PyArg_ParseTuple(args, "OO", &data_obj, &inlined_obj))
8d44b5a2974f parsers: fix refcount leak, simplify init of index (issue3417)
Bryan O'Sullivan <bryano@fb.com>
parents: 16437
diff changeset
   989
		return -1;
8d44b5a2974f parsers: fix refcount leak, simplify init of index (issue3417)
Bryan O'Sullivan <bryano@fb.com>
parents: 16437
diff changeset
   990
	if (!PyString_Check(data_obj)) {
8d44b5a2974f parsers: fix refcount leak, simplify init of index (issue3417)
Bryan O'Sullivan <bryano@fb.com>
parents: 16437
diff changeset
   991
		PyErr_SetString(PyExc_TypeError, "data is not a string");
8d44b5a2974f parsers: fix refcount leak, simplify init of index (issue3417)
Bryan O'Sullivan <bryano@fb.com>
parents: 16437
diff changeset
   992
		return -1;
8d44b5a2974f parsers: fix refcount leak, simplify init of index (issue3417)
Bryan O'Sullivan <bryano@fb.com>
parents: 16437
diff changeset
   993
	}
8d44b5a2974f parsers: fix refcount leak, simplify init of index (issue3417)
Bryan O'Sullivan <bryano@fb.com>
parents: 16437
diff changeset
   994
	size = PyString_GET_SIZE(data_obj);
8d44b5a2974f parsers: fix refcount leak, simplify init of index (issue3417)
Bryan O'Sullivan <bryano@fb.com>
parents: 16437
diff changeset
   995
16363
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   996
	self->inlined = inlined_obj && PyObject_IsTrue(inlined_obj);
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   997
	self->data = data_obj;
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   998
	self->cache = NULL;
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
   999
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1000
	self->added = NULL;
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1001
	self->offsets = NULL;
16414
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
  1002
	self->nt = NULL;
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
  1003
	self->ntlength = self->ntcapacity = 0;
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
  1004
	self->ntdepth = self->ntsplits = 0;
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
  1005
	self->ntlookups = self->ntmisses = 0;
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
  1006
	self->ntrev = -1;
16597
b767382a8675 parsers: fix refcount bug on corrupt index
Matt Mackall <mpm@selenic.com>
parents: 16572
diff changeset
  1007
	Py_INCREF(self->data);
7108
1ca878d7b849 C implementation of revlog index parsing
Bernhard Leiner <bleiner@gmail.com>
parents: 7093
diff changeset
  1008
16363
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1009
	if (self->inlined) {
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1010
		long len = inline_scan(self, NULL);
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1011
		if (len == -1)
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1012
			goto bail;
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1013
		self->raw_length = len;
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1014
		self->length = len + 1;
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1015
	} else {
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1016
		if (size % 64) {
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1017
			PyErr_SetString(PyExc_ValueError, "corrupt index file");
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1018
			goto bail;
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1019
		}
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1020
		self->raw_length = size / 64;
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1021
		self->length = self->raw_length + 1;
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1022
	}
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1023
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1024
	return 0;
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1025
bail:
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1026
	return -1;
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1027
}
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1028
16414
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
  1029
static PyObject *index_nodemap(indexObject *self)
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
  1030
{
16572
8d44b5a2974f parsers: fix refcount leak, simplify init of index (issue3417)
Bryan O'Sullivan <bryano@fb.com>
parents: 16437
diff changeset
  1031
	Py_INCREF(self);
16414
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
  1032
	return (PyObject *)self;
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
  1033
}
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
  1034
16363
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1035
static void index_dealloc(indexObject *self)
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1036
{
16370
28bb4daf070c parsers: fix a memleak, and add a clearcaches method to the index
Bryan O'Sullivan <bryano@fb.com>
parents: 16363
diff changeset
  1037
	_index_clearcaches(self);
16363
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1038
	Py_DECREF(self->data);
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1039
	Py_XDECREF(self->added);
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1040
	PyObject_Del(self);
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1041
}
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1042
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1043
static PySequenceMethods index_sequence_methods = {
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1044
	(lenfunc)index_length,   /* sq_length */
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1045
	0,                       /* sq_concat */
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1046
	0,                       /* sq_repeat */
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1047
	(ssizeargfunc)index_get, /* sq_item */
16414
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
  1048
	0,                       /* sq_slice */
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
  1049
	0,                       /* sq_ass_item */
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
  1050
	0,                       /* sq_ass_slice */
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
  1051
	(objobjproc)index_contains, /* sq_contains */
16363
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1052
};
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1053
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1054
static PyMappingMethods index_mapping_methods = {
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1055
	(lenfunc)index_length,                 /* mp_length */
16414
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
  1056
	(binaryfunc)index_getitem,             /* mp_subscript */
16363
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1057
	(objobjargproc)index_assign_subscript, /* mp_ass_subscript */
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1058
};
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1059
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1060
static PyMethodDef index_methods[] = {
16370
28bb4daf070c parsers: fix a memleak, and add a clearcaches method to the index
Bryan O'Sullivan <bryano@fb.com>
parents: 16363
diff changeset
  1061
	{"clearcaches", (PyCFunction)index_clearcaches, METH_NOARGS,
28bb4daf070c parsers: fix a memleak, and add a clearcaches method to the index
Bryan O'Sullivan <bryano@fb.com>
parents: 16363
diff changeset
  1062
	 "clear the index caches"},
16414
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
  1063
	{"get", (PyCFunction)index_m_get, METH_VARARGS,
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
  1064
	 "get an index entry"},
16363
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1065
	{"insert", (PyCFunction)index_insert, METH_VARARGS,
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1066
	 "insert an index entry"},
16414
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
  1067
	{"stats", (PyCFunction)index_stats, METH_NOARGS,
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
  1068
	 "stats for the index"},
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
  1069
	{NULL} /* Sentinel */
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
  1070
};
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
  1071
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
  1072
static PyGetSetDef index_getset[] = {
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
  1073
	{"nodemap", (getter)index_nodemap, NULL, "nodemap", NULL},
16363
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1074
	{NULL} /* Sentinel */
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1075
};
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1076
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1077
static PyTypeObject indexType = {
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1078
	PyObject_HEAD_INIT(NULL)
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1079
	0,                         /* ob_size */
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1080
	"parsers.index",           /* tp_name */
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1081
	sizeof(indexObject),       /* tp_basicsize */
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1082
	0,                         /* tp_itemsize */
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1083
	(destructor)index_dealloc, /* tp_dealloc */
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1084
	0,                         /* tp_print */
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1085
	0,                         /* tp_getattr */
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1086
	0,                         /* tp_setattr */
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1087
	0,                         /* tp_compare */
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1088
	0,                         /* tp_repr */
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1089
	0,                         /* tp_as_number */
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1090
	&index_sequence_methods,   /* tp_as_sequence */
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1091
	&index_mapping_methods,    /* tp_as_mapping */
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1092
	0,                         /* tp_hash */
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1093
	0,                         /* tp_call */
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1094
	0,                         /* tp_str */
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1095
	0,                         /* tp_getattro */
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1096
	0,                         /* tp_setattro */
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1097
	0,                         /* tp_as_buffer */
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1098
	Py_TPFLAGS_DEFAULT,        /* tp_flags */
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1099
	"revlog index",            /* tp_doc */
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1100
	0,                         /* tp_traverse */
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1101
	0,                         /* tp_clear */
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1102
	0,                         /* tp_richcompare */
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1103
	0,                         /* tp_weaklistoffset */
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1104
	0,                         /* tp_iter */
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1105
	0,                         /* tp_iternext */
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1106
	index_methods,             /* tp_methods */
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1107
	0,                         /* tp_members */
16414
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
  1108
	index_getset,              /* tp_getset */
16363
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1109
	0,                         /* tp_base */
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1110
	0,                         /* tp_dict */
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1111
	0,                         /* tp_descr_get */
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1112
	0,                         /* tp_descr_set */
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1113
	0,                         /* tp_dictoffset */
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1114
	(initproc)index_init,      /* tp_init */
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1115
	0,                         /* tp_alloc */
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1116
};
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1117
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1118
/*
16414
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
  1119
 * returns a tuple of the form (index, index, cache) with elements as
16363
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1120
 * follows:
7108
1ca878d7b849 C implementation of revlog index parsing
Bernhard Leiner <bleiner@gmail.com>
parents: 7093
diff changeset
  1121
 *
16414
e8d37b78acfb parsers: use base-16 trie for faster node->rev mapping
Bryan O'Sullivan <bryano@fb.com>
parents: 16393
diff changeset
  1122
 * index: an index object that lazily parses RevlogNG records
16363
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1123
 * cache: if data is inlined, a tuple (index_file_content, 0), else None
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1124
 *
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1125
 * added complications are for backwards compatibility
7108
1ca878d7b849 C implementation of revlog index parsing
Bernhard Leiner <bleiner@gmail.com>
parents: 7093
diff changeset
  1126
 */
13254
5ef5eb1f3515 revlog: only build the nodemap on demand
Matt Mackall <mpm@selenic.com>
parents: 11361
diff changeset
  1127
static PyObject *parse_index2(PyObject *self, PyObject *args)
7108
1ca878d7b849 C implementation of revlog index parsing
Bernhard Leiner <bleiner@gmail.com>
parents: 7093
diff changeset
  1128
{
16572
8d44b5a2974f parsers: fix refcount leak, simplify init of index (issue3417)
Bryan O'Sullivan <bryano@fb.com>
parents: 16437
diff changeset
  1129
	PyObject *tuple = NULL, *cache = NULL;
16363
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1130
	indexObject *idx;
16572
8d44b5a2974f parsers: fix refcount leak, simplify init of index (issue3417)
Bryan O'Sullivan <bryano@fb.com>
parents: 16437
diff changeset
  1131
	int ret;
16363
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1132
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1133
	idx = PyObject_New(indexObject, &indexType);
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1134
	if (idx == NULL)
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1135
		goto bail;
7108
1ca878d7b849 C implementation of revlog index parsing
Bernhard Leiner <bleiner@gmail.com>
parents: 7093
diff changeset
  1136
16572
8d44b5a2974f parsers: fix refcount leak, simplify init of index (issue3417)
Bryan O'Sullivan <bryano@fb.com>
parents: 16437
diff changeset
  1137
	ret = index_init(idx, args);
8d44b5a2974f parsers: fix refcount leak, simplify init of index (issue3417)
Bryan O'Sullivan <bryano@fb.com>
parents: 16437
diff changeset
  1138
	if (ret == -1)
16363
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1139
		goto bail;
7108
1ca878d7b849 C implementation of revlog index parsing
Bernhard Leiner <bleiner@gmail.com>
parents: 7093
diff changeset
  1140
16363
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1141
	if (idx->inlined) {
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1142
		cache = Py_BuildValue("iO", 0, idx->data);
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1143
		if (cache == NULL)
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1144
			goto bail;
7108
1ca878d7b849 C implementation of revlog index parsing
Bernhard Leiner <bleiner@gmail.com>
parents: 7093
diff changeset
  1145
	} else {
1ca878d7b849 C implementation of revlog index parsing
Bernhard Leiner <bleiner@gmail.com>
parents: 7093
diff changeset
  1146
		cache = Py_None;
16363
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1147
		Py_INCREF(cache);
7108
1ca878d7b849 C implementation of revlog index parsing
Bernhard Leiner <bleiner@gmail.com>
parents: 7093
diff changeset
  1148
	}
1ca878d7b849 C implementation of revlog index parsing
Bernhard Leiner <bleiner@gmail.com>
parents: 7093
diff changeset
  1149
16363
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1150
	tuple = Py_BuildValue("NN", idx, cache);
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1151
	if (!tuple)
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1152
		goto bail;
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1153
	return tuple;
7108
1ca878d7b849 C implementation of revlog index parsing
Bernhard Leiner <bleiner@gmail.com>
parents: 7093
diff changeset
  1154
16363
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1155
bail:
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1156
	Py_XDECREF(idx);
7108
1ca878d7b849 C implementation of revlog index parsing
Bernhard Leiner <bleiner@gmail.com>
parents: 7093
diff changeset
  1157
	Py_XDECREF(cache);
16363
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1158
	Py_XDECREF(tuple);
7108
1ca878d7b849 C implementation of revlog index parsing
Bernhard Leiner <bleiner@gmail.com>
parents: 7093
diff changeset
  1159
	return NULL;
1ca878d7b849 C implementation of revlog index parsing
Bernhard Leiner <bleiner@gmail.com>
parents: 7093
diff changeset
  1160
}
1ca878d7b849 C implementation of revlog index parsing
Bernhard Leiner <bleiner@gmail.com>
parents: 7093
diff changeset
  1161
6389
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
  1162
static char parsers_doc[] = "Efficient content parsing.";
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
  1163
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
  1164
static PyMethodDef methods[] = {
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
  1165
	{"parse_manifest", parse_manifest, METH_VARARGS, "parse a manifest\n"},
7093
16bafcebd3d1 dirstate: C parsing extension
Matt Mackall <mpm@selenic.com>
parents: 7092
diff changeset
  1166
	{"parse_dirstate", parse_dirstate, METH_VARARGS, "parse a dirstate\n"},
13254
5ef5eb1f3515 revlog: only build the nodemap on demand
Matt Mackall <mpm@selenic.com>
parents: 11361
diff changeset
  1167
	{"parse_index2", parse_index2, METH_VARARGS, "parse a revlog index\n"},
6389
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
  1168
	{NULL, NULL}
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
  1169
};
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
  1170
16363
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1171
static void module_init(PyObject *mod)
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1172
{
16604
48e42f984074 parsers: statically initializing tp_new to PyType_GenericNew is not portable
Adrian Buehlmann <adrian@cadifra.com>
parents: 16597
diff changeset
  1173
	indexType.tp_new = PyType_GenericNew;
16363
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1174
	if (PyType_Ready(&indexType) < 0)
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1175
		return;
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1176
	Py_INCREF(&indexType);
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1177
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1178
	PyModule_AddObject(mod, "index", (PyObject *)&indexType);
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1179
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1180
	nullentry = Py_BuildValue("iiiiiiis#", 0, 0, 0,
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1181
				  -1, -1, -1, -1, nullid, 20);
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1182
	if (nullentry)
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1183
		PyObject_GC_UnTrack(nullentry);
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1184
}
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1185
11361
3de3d670d2b6 parsers.c: Added support for py3k.
Renato Cunha <renatoc@gmail.com>
parents: 10449
diff changeset
  1186
#ifdef IS_PY3K
3de3d670d2b6 parsers.c: Added support for py3k.
Renato Cunha <renatoc@gmail.com>
parents: 10449
diff changeset
  1187
static struct PyModuleDef parsers_module = {
3de3d670d2b6 parsers.c: Added support for py3k.
Renato Cunha <renatoc@gmail.com>
parents: 10449
diff changeset
  1188
	PyModuleDef_HEAD_INIT,
3de3d670d2b6 parsers.c: Added support for py3k.
Renato Cunha <renatoc@gmail.com>
parents: 10449
diff changeset
  1189
	"parsers",
3de3d670d2b6 parsers.c: Added support for py3k.
Renato Cunha <renatoc@gmail.com>
parents: 10449
diff changeset
  1190
	parsers_doc,
3de3d670d2b6 parsers.c: Added support for py3k.
Renato Cunha <renatoc@gmail.com>
parents: 10449
diff changeset
  1191
	-1,
3de3d670d2b6 parsers.c: Added support for py3k.
Renato Cunha <renatoc@gmail.com>
parents: 10449
diff changeset
  1192
	methods
3de3d670d2b6 parsers.c: Added support for py3k.
Renato Cunha <renatoc@gmail.com>
parents: 10449
diff changeset
  1193
};
3de3d670d2b6 parsers.c: Added support for py3k.
Renato Cunha <renatoc@gmail.com>
parents: 10449
diff changeset
  1194
3de3d670d2b6 parsers.c: Added support for py3k.
Renato Cunha <renatoc@gmail.com>
parents: 10449
diff changeset
  1195
PyMODINIT_FUNC PyInit_parsers(void)
3de3d670d2b6 parsers.c: Added support for py3k.
Renato Cunha <renatoc@gmail.com>
parents: 10449
diff changeset
  1196
{
16363
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1197
	PyObject *mod = PyModule_Create(&parsers_module);
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1198
	module_init(mod);
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1199
	return mod;
11361
3de3d670d2b6 parsers.c: Added support for py3k.
Renato Cunha <renatoc@gmail.com>
parents: 10449
diff changeset
  1200
}
3de3d670d2b6 parsers.c: Added support for py3k.
Renato Cunha <renatoc@gmail.com>
parents: 10449
diff changeset
  1201
#else
6389
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
  1202
PyMODINIT_FUNC initparsers(void)
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
  1203
{
16363
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1204
	PyObject *mod = Py_InitModule3("parsers", methods, parsers_doc);
2cdd7e63211b parsers: incrementally parse the revlog index in C
Bryan O'Sullivan <bryano@fb.com>
parents: 15033
diff changeset
  1205
	module_init(mod);
6389
0231f763ebc8 manifest: improve parsing performance by 8x via a new C extension
Bryan O'Sullivan <bos@serpentine.com>
parents:
diff changeset
  1206
}
11361
3de3d670d2b6 parsers.c: Added support for py3k.
Renato Cunha <renatoc@gmail.com>
parents: 10449
diff changeset
  1207
#endif