mercurial/bdiff_module.c

obsolescence: add test case B-5 for obsolescence markers exchange

About 3 years ago, in August 2014, the logic to select what markers to select on
push was ported from the evolve extension to Mercurial core. However, for some
unclear reasons, the tests for that logic were not ported alongside.
I realised it a couple of weeks ago while working on another push related issue.
I've made a clean up pass on the tests and they are now ready to integrate the
core test suite. This series of changesets do not change any logic. I just adds
test for logic that has been around for about 10 versions of Mercurial.

They are a patch for each test case. It makes it easier to review and postpone
one with documentation issues without rejecting the wholes series.

This patch introduce B-5:

    Push of a children of changeset which successors is pruned

Each test case comes it in own test file. It help parallelism and does not
introduce a significant overhead from having a single unified giant test file.
Here are timing  to support this claim.

# Multiple test files version:
# run-tests.py --local -j 1 test-exchange-*.t
53.40s user 6.82s system 85% cpu 1:10.76 total
52.79s user 6.97s system 85% cpu 1:09.97 total
52.94s user 6.82s system 85% cpu 1:09.69 total

# Single test file version:
# run-tests.py --local -j 1 test-exchange-obsmarkers.t
52.97s user 6.85s system 85% cpu 1:10.10 total
52.64s user 6.79s system 85% cpu 1:09.63 total
53.70s user 7.00s system 85% cpu 1:11.17 total

/*
 bdiff.c - efficient binary diff extension for Mercurial

 Copyright 2005, 2006 Matt Mackall <[e-mail]>

 This software may be used and distributed according to the terms of
 the GNU General Public License, incorporated herein by reference.

 Based roughly on Python difflib
*/

#define PY_SSIZE_T_CLEAN
#include <Python.h>
#include <stdlib.h>
#include <string.h>
#include <limits.h>

#include "bdiff.h"
#include "bitmanipulation.h"
#include "util.h"


static PyObject *blocks(PyObject *self, PyObject *args)
{
	PyObject *sa, *sb, *rl = NULL, *m;
	struct bdiff_line *a, *b;
	struct bdiff_hunk l, *h;
	int an, bn, count, pos = 0;

	l.next = NULL;

	if (!PyArg_ParseTuple(args, "SS:bdiff", &sa, &sb))
		return NULL;

	an = bdiff_splitlines(PyBytes_AsString(sa), PyBytes_Size(sa), &a);
	bn = bdiff_splitlines(PyBytes_AsString(sb), PyBytes_Size(sb), &b);

	if (!a || !b)
		goto nomem;

	count = bdiff_diff(a, an, b, bn, &l);
	if (count < 0)
		goto nomem;

	rl = PyList_New(count);
	if (!rl)
		goto nomem;

	for (h = l.next; h; h = h->next) {
		m = Py_BuildValue("iiii", h->a1, h->a2, h->b1, h->b2);
		PyList_SetItem(rl, pos, m);
		pos++;
	}

nomem:
	free(a);
	free(b);
	bdiff_freehunks(l.next);
	return rl ? rl : PyErr_NoMemory();
}

static PyObject *bdiff(PyObject *self, PyObject *args)
{
	char *sa, *sb, *rb, *ia, *ib;
	PyObject *result = NULL;
	struct bdiff_line *al, *bl;
	struct bdiff_hunk l, *h;
	int an, bn, count;
	Py_ssize_t len = 0, la, lb, li = 0, lcommon = 0, lmax;
	PyThreadState *_save;

	l.next = NULL;

	if (!PyArg_ParseTuple(args, "s#s#:bdiff", &sa, &la, &sb, &lb))
		return NULL;

	if (la > UINT_MAX || lb > UINT_MAX) {
		PyErr_SetString(PyExc_ValueError, "bdiff inputs too large");
		return NULL;
	}

	_save = PyEval_SaveThread();

	lmax = la > lb ? lb : la;
	for (ia = sa, ib = sb;
	     li < lmax && *ia == *ib;
	     ++li, ++ia, ++ib)
		if (*ia == '\n')
			lcommon = li + 1;
	/* we can almost add: if (li == lmax) lcommon = li; */

	an = bdiff_splitlines(sa + lcommon, la - lcommon, &al);
	bn = bdiff_splitlines(sb + lcommon, lb - lcommon, &bl);
	if (!al || !bl)
		goto nomem;

	count = bdiff_diff(al, an, bl, bn, &l);
	if (count < 0)
		goto nomem;

	/* calculate length of output */
	la = lb = 0;
	for (h = l.next; h; h = h->next) {
		if (h->a1 != la || h->b1 != lb)
			len += 12 + bl[h->b1].l - bl[lb].l;
		la = h->a2;
		lb = h->b2;
	}
	PyEval_RestoreThread(_save);
	_save = NULL;

	result = PyBytes_FromStringAndSize(NULL, len);

	if (!result)
		goto nomem;

	/* build binary patch */
	rb = PyBytes_AsString(result);
	la = lb = 0;

	for (h = l.next; h; h = h->next) {
		if (h->a1 != la || h->b1 != lb) {
			len = bl[h->b1].l - bl[lb].l;
			putbe32((uint32_t)(al[la].l + lcommon - al->l), rb);
			putbe32((uint32_t)(al[h->a1].l + lcommon - al->l), rb + 4);
			putbe32((uint32_t)len, rb + 8);
			memcpy(rb + 12, bl[lb].l, len);
			rb += 12 + len;
		}
		la = h->a2;
		lb = h->b2;
	}

nomem:
	if (_save)
		PyEval_RestoreThread(_save);
	free(al);
	free(bl);
	bdiff_freehunks(l.next);
	return result ? result : PyErr_NoMemory();
}

/*
 * If allws != 0, remove all whitespace (' ', \t and \r). Otherwise,
 * reduce whitespace sequences to a single space and trim remaining whitespace
 * from end of lines.
 */
static PyObject *fixws(PyObject *self, PyObject *args)
{
	PyObject *s, *result = NULL;
	char allws, c;
	const char *r;
	Py_ssize_t i, rlen, wlen = 0;
	char *w;

	if (!PyArg_ParseTuple(args, "Sb:fixws", &s, &allws))
		return NULL;
	r = PyBytes_AsString(s);
	rlen = PyBytes_Size(s);

	w = (char *)PyMem_Malloc(rlen ? rlen : 1);
	if (!w)
		goto nomem;

	for (i = 0; i != rlen; i++) {
		c = r[i];
		if (c == ' ' || c == '\t' || c == '\r') {
			if (!allws && (wlen == 0 || w[wlen - 1] != ' '))
				w[wlen++] = ' ';
		} else if (c == '\n' && !allws
			  && wlen > 0 && w[wlen - 1] == ' ') {
			w[wlen - 1] = '\n';
		} else {
			w[wlen++] = c;
		}
	}

	result = PyBytes_FromStringAndSize(w, wlen);

nomem:
	PyMem_Free(w);
	return result ? result : PyErr_NoMemory();
}


static char mdiff_doc[] = "Efficient binary diff.";

static PyMethodDef methods[] = {
	{"bdiff", bdiff, METH_VARARGS, "calculate a binary diff\n"},
	{"blocks", blocks, METH_VARARGS, "find a list of matching lines\n"},
	{"fixws", fixws, METH_VARARGS, "normalize diff whitespaces\n"},
	{NULL, NULL}
};

#ifdef IS_PY3K
static struct PyModuleDef bdiff_module = {
	PyModuleDef_HEAD_INIT,
	"bdiff",
	mdiff_doc,
	-1,
	methods
};

PyMODINIT_FUNC PyInit_bdiff(void)
{
	return PyModule_Create(&bdiff_module);
}
#else
PyMODINIT_FUNC initbdiff(void)
{
	Py_InitModule3("bdiff", methods, mdiff_doc);
}
#endif