view mercurial/bdiff_module.c @ 31793:69d8fcf20014

help: document bundle specifications

I softly formalized the concept of a "bundle specification" a while
ago when I was working on clone bundles and stream clone bundles and
wanted a more robust way to define what exactly is in a bundle file.

The concept has existed for a while. Since it is part of the clone
bundles feature and exposed to the user via the "-t" argument to
`hg bundle`, it is something we need to support for the long haul.

After the 4.1 release, I heard a few people comment that they didn't
realize you could generate zstd bundles with `hg bundle`. I'm
partially to blame for not documenting it in bundle's docstring.

Additionally, I added a hacky, experimental feature for controlling
the compression level of bundles in 76104a4899ad. As the commit
message says, I went with a quick and dirty solution out of time
constraints. Furthermore, I wanted to eventually store this
configuration in the "bundlespec" so it could be made more flexible.

Given:

a) bundlespecs are here to stay
b) we don't have great documentation over what they are, despite being
   a user-facing feature
c) the list of available compression engines and their behavior isn't
   exposed
d) we need an extensible place to modify behavior of compression
   engines

I want to move forward with formalizing bundlespecs as a user-facing
feature. This commit does that by introducing a "bundlespec" help
page. Leaning on the just-added compression engine documentation
and API, the topic also conveniently lists available compression
engines and details about them. This makes features like zstd
bundle compression more discoverable. e.g. you can now
`hg help -k zstd` and it lists the "bundlespec" topic.

/*
 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