mercurial/bdiff_module.c

httppeer: use compression engine API for decompressing responses

In preparation for supporting multiple compression formats on the
wire protocol, we need all users of the wire protocol to use
compression engine APIs.

This commit ports the HTTP wire protocol client to use the
compression engine API.

The code for handling the HTTPException is a bit hacky. Essentially,
HTTPException could be thrown by any read() from the socket. However,
as part of porting the API, we no longer have a generator wrapping
the socket and we don't have a single place where we can trap the
exception. We solve this by introducing a proxy class that intercepts
read() and converts the exception appropriately.

In the future, we could introduce a new compression engine API that
supports emitting a generator of decompressed chunks. This would
eliminate the need for the proxy class. As I said when I introduced
the decompressorreader() API, I'm not fond of it and would support
transitioning to something better. This can be done as a follow-up,
preferably once all the code is using the compression engine API and
we have a better idea of the API needs of all the consumers.

/*
 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;
	PyObject *result = NULL;
	struct bdiff_line *al, *bl;
	struct bdiff_hunk l, *h;
	int an, bn, count;
	Py_ssize_t len = 0, la, lb;
	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();
	an = bdiff_splitlines(sa, la, &al);
	bn = bdiff_splitlines(sb, lb, &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 - al->l), rb);
			putbe32((uint32_t)(al[h->a1].l - 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 *)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:
	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