/*

 parsers.c - efficient content parsing

 Copyright 2008 Matt Mackall <mpm@selenic.com> and others

 This software may be used and distributed according to the terms of

 the GNU General Public License, incorporated herein by reference.

*/

#include <Python.h>

#include <ctype.h>

#include <stddef.h>

#include <string.h>

#include "util.h"

static char *versionerrortext = "Python minor version mismatch";

static int8_t hextable[256] = {

	-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,

	-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,

	-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,

	 0,  1,  2,  3,  4,  5,  6,  7,  8,  9, -1, -1, -1, -1, -1, -1, /* 0-9 */

	-1, 10, 11, 12, 13, 14, 15, -1, -1, -1, -1, -1, -1, -1, -1, -1, /* A-F */

	-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,

	-1, 10, 11, 12, 13, 14, 15, -1, -1, -1, -1, -1, -1, -1, -1, -1, /* a-f */

	-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,

	-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,

	-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,

	-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,

	-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,

	-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,

	-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,

	-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,

	-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1

};

static char lowertable[128] = {

	'\x00', '\x01', '\x02', '\x03', '\x04', '\x05', '\x06', '\x07',

	'\x08', '\x09', '\x0a', '\x0b', '\x0c', '\x0d', '\x0e', '\x0f',

	'\x10', '\x11', '\x12', '\x13', '\x14', '\x15', '\x16', '\x17',

	'\x18', '\x19', '\x1a', '\x1b', '\x1c', '\x1d', '\x1e', '\x1f',

	'\x20', '\x21', '\x22', '\x23', '\x24', '\x25', '\x26', '\x27',

	'\x28', '\x29', '\x2a', '\x2b', '\x2c', '\x2d', '\x2e', '\x2f',

	'\x30', '\x31', '\x32', '\x33', '\x34', '\x35', '\x36', '\x37',

	'\x38', '\x39', '\x3a', '\x3b', '\x3c', '\x3d', '\x3e', '\x3f',

	'\x40',

	        '\x61', '\x62', '\x63', '\x64', '\x65', '\x66', '\x67', /* A-G */

	'\x68', '\x69', '\x6a', '\x6b', '\x6c', '\x6d', '\x6e', '\x6f', /* H-O */

	'\x70', '\x71', '\x72', '\x73', '\x74', '\x75', '\x76', '\x77', /* P-W */

	'\x78', '\x79', '\x7a',                                         /* X-Z */

	                        '\x5b', '\x5c', '\x5d', '\x5e', '\x5f',

	'\x60', '\x61', '\x62', '\x63', '\x64', '\x65', '\x66', '\x67',

	'\x68', '\x69', '\x6a', '\x6b', '\x6c', '\x6d', '\x6e', '\x6f',

	'\x70', '\x71', '\x72', '\x73', '\x74', '\x75', '\x76', '\x77',

	'\x78', '\x79', '\x7a', '\x7b', '\x7c', '\x7d', '\x7e', '\x7f'

};

static inline int hexdigit(const char *p, Py_ssize_t off)

{

	int8_t val = hextable[(unsigned char)p[off]];

	if (val >= 0) {

		return val;

	}

	PyErr_SetString(PyExc_ValueError, "input contains non-hex character");

	return 0;

}

/*

 * Turn a hex-encoded string into binary.

 */

static PyObject *unhexlify(const char *str, int len)

{

	PyObject *ret;

	char *d;

	int i;

	ret = PyBytes_FromStringAndSize(NULL, len / 2);

	if (!ret)

		return NULL;

	d = PyBytes_AsString(ret);

	for (i = 0; i < len;) {

		int hi = hexdigit(str, i++);

		int lo = hexdigit(str, i++);

		*d++ = (hi << 4) | lo;

	}

	return ret;

}

static PyObject *asciilower(PyObject *self, PyObject *args)

{

	char *str, *newstr;

	int i, len;

	PyObject *newobj = NULL;

	if (!PyArg_ParseTuple(args, "s#", &str, &len))

		goto quit;

	newobj = PyBytes_FromStringAndSize(NULL, len);

	if (!newobj)

		goto quit;

	newstr = PyBytes_AS_STRING(newobj);

	for (i = 0; i < len; i++) {

		char c = str[i];

		if (c & 0x80) {

			PyObject *err = PyUnicodeDecodeError_Create(

				"ascii", str, len, i, (i + 1),

				"unexpected code byte");

			PyErr_SetObject(PyExc_UnicodeDecodeError, err);

			Py_XDECREF(err);

			goto quit;

		}

		newstr[i] = lowertable[(unsigned char)c];

	}

	return newobj;

quit:

	Py_XDECREF(newobj);

	return NULL;

}

/*

 * This code assumes that a manifest is stitched together with newline

 * ('\n') characters.

 */

static PyObject *parse_manifest(PyObject *self, PyObject *args)

{

	PyObject *mfdict, *fdict;

	char *str, *start, *end;

	int len;

	if (!PyArg_ParseTuple(args, "O!O!s#:parse_manifest",

			      &PyDict_Type, &mfdict,

			      &PyDict_Type, &fdict,

			      &str, &len))

		goto quit;

	start = str;

	end = str + len;

	while (start < end) {

		PyObject *file = NULL, *node = NULL;

		PyObject *flags = NULL;

		char *zero = NULL, *newline = NULL;

		ptrdiff_t nlen;

		zero = memchr(start, '\0', end - start);

		if (!zero) {

			PyErr_SetString(PyExc_ValueError,

					"manifest entry has no separator");

			goto quit;

		}

		newline = memchr(zero + 1, '\n', end - (zero + 1));

		if (!newline) {

			PyErr_SetString(PyExc_ValueError,

					"manifest contains trailing garbage");

			goto quit;

		}

		file = PyBytes_FromStringAndSize(start, zero - start);

		if (!file)

			goto bail;

		nlen = newline - zero - 1;

		node = unhexlify(zero + 1, nlen > 40 ? 40 : (int)nlen);

		if (!node)

			goto bail;

		if (nlen > 40) {

			flags = PyBytes_FromStringAndSize(zero + 41,

							   nlen - 40);

			if (!flags)

				goto bail;

			if (PyDict_SetItem(fdict, file, flags) == -1)

				goto bail;

		}

		if (PyDict_SetItem(mfdict, file, node) == -1)

			goto bail;

		start = newline + 1;

		Py_XDECREF(flags);

		Py_XDECREF(node);

		Py_XDECREF(file);

		continue;

	bail:

		Py_XDECREF(flags);

		Py_XDECREF(node);

		Py_XDECREF(file);

		goto quit;

	}

	Py_INCREF(Py_None);

	return Py_None;

quit:

	return NULL;

}

static inline dirstateTupleObject *make_dirstate_tuple(char state, int mode,

						       int size, int mtime)

{

	dirstateTupleObject *t = PyObject_New(dirstateTupleObject,

					      &dirstateTupleType);

	if (!t)

		return NULL;

	t->state = state;

	t->mode = mode;

	t->size = size;

	t->mtime = mtime;

	return t;

}

static PyObject *dirstate_tuple_new(PyTypeObject *subtype, PyObject *args,

				    PyObject *kwds)

{

	/* We do all the initialization here and not a tp_init function because

	 * dirstate_tuple is immutable. */

	dirstateTupleObject *t;

	char state;

	int size, mode, mtime;

	if (!PyArg_ParseTuple(args, "ciii", &state, &mode, &size, &mtime))

		return NULL;

	t = (dirstateTupleObject *)subtype->tp_alloc(subtype, 1);

	if (!t)

		return NULL;

	t->state = state;

	t->mode = mode;

	t->size = size;

	t->mtime = mtime;

	return (PyObject *)t;

}

static void dirstate_tuple_dealloc(PyObject *o)

{

	PyObject_Del(o);

}

static Py_ssize_t dirstate_tuple_length(PyObject *o)

{

	return 4;

}

static PyObject *dirstate_tuple_item(PyObject *o, Py_ssize_t i)

{

	dirstateTupleObject *t = (dirstateTupleObject *)o;

	switch (i) {

	case 0:

		return PyBytes_FromStringAndSize(&t->state, 1);

	case 1:

		return PyInt_FromLong(t->mode);

	case 2:

		return PyInt_FromLong(t->size);

	case 3:

		return PyInt_FromLong(t->mtime);

	default:

		PyErr_SetString(PyExc_IndexError, "index out of range");

		return NULL;

	}

}

static PySequenceMethods dirstate_tuple_sq = {

	dirstate_tuple_length,     /* sq_length */

	0,                         /* sq_concat */

	0,                         /* sq_repeat */

	dirstate_tuple_item,       /* sq_item */

	0,                         /* sq_ass_item */

	0,                         /* sq_contains */

	0,                         /* sq_inplace_concat */

	0                          /* sq_inplace_repeat */

};

PyTypeObject dirstateTupleType = {

	PyVarObject_HEAD_INIT(NULL, 0)

	"dirstate_tuple",          /* tp_name */

	sizeof(dirstateTupleObject),/* tp_basicsize */

	0,                         /* tp_itemsize */

	(destructor)dirstate_tuple_dealloc, /* tp_dealloc */

	0,                         /* tp_print */

	0,                         /* tp_getattr */

	0,                         /* tp_setattr */

	0,                         /* tp_compare */

	0,                         /* tp_repr */

	0,                         /* tp_as_number */

	&dirstate_tuple_sq,        /* tp_as_sequence */

	0,                         /* tp_as_mapping */

	0,                         /* tp_hash  */

	0,                         /* tp_call */

	0,                         /* tp_str */

	0,                         /* tp_getattro */

	0,                         /* tp_setattro */

	0,                         /* tp_as_buffer */

	Py_TPFLAGS_DEFAULT,        /* tp_flags */

	"dirstate tuple",          /* tp_doc */

	0,                         /* tp_traverse */

	0,                         /* tp_clear */

	0,                         /* tp_richcompare */

	0,                         /* tp_weaklistoffset */

	0,                         /* tp_iter */

	0,                         /* tp_iternext */

	0,                         /* tp_methods */

	0,                         /* tp_members */

	0,                         /* tp_getset */

	0,                         /* tp_base */

	0,                         /* tp_dict */

	0,                         /* tp_descr_get */

	0,                         /* tp_descr_set */

	0,                         /* tp_dictoffset */

	0,                         /* tp_init */

	0,                         /* tp_alloc */

	dirstate_tuple_new,        /* tp_new */

};

static PyObject *parse_dirstate(PyObject *self, PyObject *args)

{

	PyObject *dmap, *cmap, *parents = NULL, *ret = NULL;

	PyObject *fname = NULL, *cname = NULL, *entry = NULL;

	char state, *cur, *str, *cpos;

	int mode, size, mtime;

	unsigned int flen, len, pos = 40;

	int readlen;

	if (!PyArg_ParseTuple(args, "O!O!s#:parse_dirstate",

			      &PyDict_Type, &dmap,

			      &PyDict_Type, &cmap,

			      &str, &readlen))

		goto quit;

	if (readlen < 0)

		goto quit;

	len = readlen;

	/* read parents */

	if (len < 40)

		goto quit;

	parents = Py_BuildValue("s#s#", str, 20, str + 20, 20);

	if (!parents)

		goto quit;

	/* read filenames */

	while (pos >= 40 && pos < len) {

		cur = str + pos;

		/* unpack header */

		state = *cur;

		mode = getbe32(cur + 1);

		size = getbe32(cur + 5);

		mtime = getbe32(cur + 9);

		flen = getbe32(cur + 13);

		pos += 17;