mercurial/bdiff_module.c

url: add distribution and version to user-agent request header (BC)

As a server operator, I've always wanted to know what Mercurial
version clients are running so I can track version adoption and
make informed decisions about which versions of Mercurial to
support in extensions. Unfortunately, there is no easy way to discern
this today: the best you can do is look for high-level feature usage
(e.g. bundle2) or sniff capabilities from bundle2 commands. And these
things aren't changed frequently enough to tell you anything that
interesting.

Nearly every piece of software talking HTTP sends its version in
the user agent. This includes web browsers, curl, and even Git.

This patch adds the distribution name and version to the user-agent
HTTP request header. We choose "Mercurial" for the distribution
name because that seems appropriate. The version string comes
from __version__.

The value is inside parenthesis for a few reasons:

* The version *may* contain spaces
* Alternate forms like "Mercurial/<version>" imply structure and
  since the user agent should not be used by servers for protocol
  or feature negotiation/detection, we don't want to even give the
  illusion that the value should be parsed. A free form field is
  the most hostile to parsing.

Flagging the patch as BC so it shows up in release notes. This
change should be backwards compatible. But I wouldn't be surprised if
a server somewhere is filtering on the exact old user agent string. So
I want to make noise about this change.

/*
 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"


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