/*

 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 char uppertable[128] = {

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

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

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

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

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

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

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

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

	'\x40', '\x41', '\x42', '\x43', '\x44', '\x45', '\x46', '\x47',

	'\x48', '\x49', '\x4a', '\x4b', '\x4c', '\x4d', '\x4e', '\x4f',

	'\x50', '\x51', '\x52', '\x53', '\x54', '\x55', '\x56', '\x57',

	'\x58', '\x59', '\x5a', '\x5b', '\x5c', '\x5d', '\x5e', '\x5f',

	'\x60',

		'\x41', '\x42', '\x43', '\x44', '\x45', '\x46', '\x47', /* a-g */

	'\x48', '\x49', '\x4a', '\x4b', '\x4c', '\x4d', '\x4e', '\x4f', /* h-o */

	'\x50', '\x51', '\x52', '\x53', '\x54', '\x55', '\x56', '\x57', /* p-w */

	'\x58', '\x59', '\x5a', 					/* x-z */

				'\x7b', '\x7c', '\x7d', '\x7e', '\x7f'

};

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.

 */

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 inline PyObject *_asciitransform(PyObject *str_obj,

					const char table[128],

					PyObject *fallback_fn)

{

	char *str, *newstr;

	Py_ssize_t i, len;

	PyObject *newobj = NULL;

	PyObject *ret = NULL;

	str = PyBytes_AS_STRING(str_obj);

	len = PyBytes_GET_SIZE(str_obj);

	newobj = PyBytes_FromStringAndSize(NULL, len);

	if (!newobj)

		goto quit;

	newstr = PyBytes_AS_STRING(newobj);

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

		char c = str[i];

		if (c & 0x80) {

			if (fallback_fn != NULL) {

				ret = PyObject_CallFunctionObjArgs(fallback_fn,

					str_obj, NULL);

			} else {

				PyObject *err = PyUnicodeDecodeError_Create(

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

					"unexpected code byte");

				PyErr_SetObject(PyExc_UnicodeDecodeError, err);

				Py_XDECREF(err);

			}

			goto quit;

		}

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

	}

	ret = newobj;

	Py_INCREF(ret);

quit:

	Py_XDECREF(newobj);

	return ret;

}

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

{

	PyObject *str_obj;

	if (!PyArg_ParseTuple(args, "O!:asciilower", &PyBytes_Type, &str_obj))

		return NULL;

	return _asciitransform(str_obj, lowertable, NULL);

}

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

{

	PyObject *str_obj;

	if (!PyArg_ParseTuple(args, "O!:asciiupper", &PyBytes_Type, &str_obj))

		return NULL;

	return _asciitransform(str_obj, uppertable, NULL);

}

static inline PyObject *_dict_new_presized(Py_ssize_t expected_size)

{

	/* _PyDict_NewPresized expects a minused parameter, but it actually

	   creates a dictionary that's the nearest power of two bigger than the

	   parameter. For example, with the initial minused = 1000, the

	   dictionary created has size 1024. Of course in a lot of cases that

	   can be greater than the maximum load factor Python's dict object

	   expects (= 2/3), so as soon as we cross the threshold we'll resize

	   anyway. So create a dictionary that's at least 3/2 the size. */

	return _PyDict_NewPresized(((1 + expected_size) / 2) * 3);

}

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

{

	Py_ssize_t expected_size;

	if (!PyArg_ParseTuple(args, "n:make_presized_dict", &expected_size))

		return NULL;

	return _dict_new_presized(expected_size);

}

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

{

	PyObject *dmap, *spec_obj, *normcase_fallback;

	PyObject *file_foldmap = NULL;

	enum normcase_spec spec;

	PyObject *k, *v;

	dirstateTupleObject *tuple;

	Py_ssize_t pos = 0;

	const char *table;

	if (!PyArg_ParseTuple(args, "O!O!O!:make_file_foldmap",

			      &PyDict_Type, &dmap,

			      &PyInt_Type, &spec_obj,

			      &PyFunction_Type, &normcase_fallback))

		goto quit;

	spec = (int)PyInt_AS_LONG(spec_obj);

	switch (spec) {

	case NORMCASE_LOWER:

		table = lowertable;

		break;

	case NORMCASE_UPPER:

		table = uppertable;

		break;

	case NORMCASE_OTHER:

		table = NULL;

		break;

	default:

		PyErr_SetString(PyExc_TypeError, "invalid normcasespec");

		goto quit;

	}

	/* Add some more entries to deal with additions outside this

	   function. */

	file_foldmap = _dict_new_presized((PyDict_Size(dmap) / 10) * 11);

	if (file_foldmap == NULL)

		goto quit;

	while (PyDict_Next(dmap, &pos, &k, &v)) {

		if (!dirstate_tuple_check(v)) {

			PyErr_SetString(PyExc_TypeError,

					"expected a dirstate tuple");

			goto quit;

		}

		tuple = (dirstateTupleObject *)v;

		if (tuple->state != 'r') {

			PyObject *normed;

			if (table != NULL) {

				normed = _asciitransform(k, table,

					normcase_fallback);

			} else {

				normed = PyObject_CallFunctionObjArgs(

					normcase_fallback, k, NULL);

			}

			if (normed == NULL)

				goto quit;

			if (PyDict_SetItem(file_foldmap, normed, k) == -1) {

				Py_DECREF(normed);

				goto quit;

			}

			Py_DECREF(normed);

		}

	}

	return file_foldmap;

quit:

	Py_XDECREF(file_foldmap);

	return NULL;

}

/*

 * 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,