annotate mercurial/diffhelpers.c @ 16719:e7bf09acd410

localrepo: add branchtip() method for faster single-branch lookups

For the PyPy repo with 744 branches and 843 branch heads, this brings
hg log -r default over NFS from:

   CallCount    Recursive    Total(ms)   Inline(ms) module:lineno(function)
        3249            0      1.3222      1.3222   <open>
        3244            0      0.6211      0.6211   <method 'close' of 'file' objects>
        3243            0      0.0800      0.0800   <method 'read' of 'file' objects>
        3241            0      0.0660      0.0660   <method 'seek' of 'file' objects>
        3905            0      0.0476      0.0476   <zlib.decompress>
        3281            0      2.6756      0.0472   mercurial.changelog:182(read)
       +3281            0      2.5256      0.0453   +mercurial.revlog:881(revision)
       +3276            0      0.0389      0.0196   +mercurial.changelog:28(decodeextra)
       +6562            0      0.0123      0.0123   +<method 'split' of 'str' objects>
       +6562            0      0.0408      0.0073   +mercurial.encoding:61(tolocal)
       +3281            0      0.0054      0.0054   +<method 'index' of 'str' objects>
        3241            0      2.2464      0.0456   mercurial.revlog:818(_loadchunk)
       +3241            0      0.6205      0.6205   +<method 'close' of 'file' objects>
       +3241            0      0.0765      0.0765   +<method 'read' of 'file' objects>
       +3241            0      0.0660      0.0660   +<method 'seek' of 'file' objects>
       +3241            0      1.4209      0.0135   +mercurial.store:374(__call__)
       +3241            0      0.0122      0.0107   +mercurial.revlog:810(_addchunk)
        3281            0      2.5256      0.0453   mercurial.revlog:881(revision)
       +3280            0      0.0175      0.0175   +mercurial.revlog:305(rev)
       +3281            0      2.2819      0.0119   +mercurial.revlog:847(_chunkraw)
       +3281            0      0.0603      0.0083   +mercurial.revlog:945(_checkhash)
       +3281            0      0.0051      0.0051   +mercurial.revlog:349(flags)
       +3281            0      0.0040      0.0040   +<mercurial.mpatch.patches>
       13682            0      0.0479      0.0248   <method 'decode' of 'str' objects>
       +7418            0      0.0228      0.0076   +encodings.utf_8:15(decode)
          +1            0      0.0003      0.0000   +encodings:71(search_function)
        3248            0      1.3995      0.0246   mercurial.scmutil:218(__call__)
       +3248            0      1.3222      1.3222   +<open>
       +3248            0      0.0235      0.0184   +os.path:80(split)
       +3248            0      0.0084      0.0068   +mercurial.scmutil:92(__call__)
Time: real 2.750 secs (user 0.680+0.000 sys 0.360+0.000)

down to:

   CallCount    Recursive    Total(ms)   Inline(ms) module:lineno(function)
          55           31      0.0197      0.0163   <__import__>
          +1            0      0.0006      0.0002   +mercurial.context:8(<module>)
          +1            0      0.0042      0.0001   +mercurial.revlog:12(<module>)
          +1            0      0.0002      0.0001   +mercurial.match:8(<module>)
          +1            0      0.0003      0.0001   +mercurial.dirstate:7(<module>)
          +1            0      0.0057      0.0001   +mercurial.changelog:8(<module>)
           1            0      0.0117      0.0032   mercurial.localrepo:525(_readbranchcache)
        +844            0      0.0015      0.0015   +<binascii.unhexlify>
        +845            0      0.0010      0.0010   +<method 'split' of 'str' objects>
        +843            0      0.0045      0.0009   +mercurial.encoding:61(tolocal)
        +843            0      0.0004      0.0004   +<method 'setdefault' of 'dict' objects>
          +1            0      0.0003      0.0003   +<method 'close' of 'file' objects>
           3            0      0.0029      0.0029   <method 'read' of 'file' objects>
           9            0      0.0018      0.0018   <open>
         990            0      0.0017      0.0017   <binascii.unhexlify>
          53            0      0.0016      0.0016   mercurial.demandimport:43(__init__)
         862            0      0.0015      0.0015   <_codecs.utf_8_decode>
         862            0      0.0037      0.0014   <method 'decode' of 'str' objects>
        +862            0      0.0023      0.0008   +encodings.utf_8:15(decode)
         981            0      0.0011      0.0011   <method 'split' of 'str' objects>
         861            0      0.0046      0.0009   mercurial.encoding:61(tolocal)
        +861            0      0.0037      0.0014   +<method 'decode' of 'str' objects>
         862            0      0.0023      0.0008   encodings.utf_8:15(decode)
        +862            0      0.0015      0.0015   +<_codecs.utf_8_decode>
           4            0      0.0008      0.0008   <method 'close' of 'file' objects>
         179          154      0.0202      0.0004   mercurial.demandimport:83(__getattribute__)
         +36           11      0.0199      0.0003   +mercurial.demandimport:55(_load)
         +72            0      0.0001      0.0001   +mercurial.demandimport:83(__getattribute__)
         +36            0      0.0000      0.0000   +<getattr>
           1            0      0.0015      0.0004   mercurial.tags:148(_readtagcache)
Time: real 0.060 secs (user 0.030+0.000 sys 0.010+0.000)

/*
 * diffhelpers.c - helper routines for mpatch
 *
 * Copyright 2007 Chris Mason <[e-mail]>
 *
 * This software may be used and distributed according to the terms
 * of the GNU General Public License v2, incorporated herein by reference.
 */

#include <Python.h>
#include <stdlib.h>
#include <string.h>

#include "util.h"

static char diffhelpers_doc[] = "Efficient diff parsing";
static PyObject *diffhelpers_Error;


/* fixup the last lines of a and b when the patch has no newline at eof */
static void _fix_newline(PyObject *hunk, PyObject *a, PyObject *b)
{
	Py_ssize_t hunksz = PyList_Size(hunk);
	PyObject *s = PyList_GET_ITEM(hunk, hunksz-1);
	char *l = PyBytes_AsString(s);
	Py_ssize_t alen = PyList_Size(a);
	Py_ssize_t blen = PyList_Size(b);
	char c = l[0];
	PyObject *hline;
	Py_ssize_t sz = PyBytes_GET_SIZE(s);

	if (sz > 1 && l[sz-2] == '\r')
		/* tolerate CRLF in last line */
		sz -= 1;

	hline = PyBytes_FromStringAndSize(l, sz-1);

	if (c == ' ' || c == '+') {
		PyObject *rline = PyBytes_FromStringAndSize(l + 1, sz - 2);
		PyList_SetItem(b, blen-1, rline);
	}
	if (c == ' ' || c == '-') {
		Py_INCREF(hline);
		PyList_SetItem(a, alen-1, hline);
	}
	PyList_SetItem(hunk, hunksz-1, hline);
}

/* python callable form of _fix_newline */
static PyObject *
fix_newline(PyObject *self, PyObject *args)
{
	PyObject *hunk, *a, *b;
	if (!PyArg_ParseTuple(args, "OOO", &hunk, &a, &b))
		return NULL;
	_fix_newline(hunk, a, b);
	return Py_BuildValue("l", 0);
}

#if (PY_VERSION_HEX < 0x02050000)
static const char *addlines_format = "OOiiOO";
#else
static const char *addlines_format = "OOnnOO";
#endif

/*
 * read lines from fp into the hunk.  The hunk is parsed into two arrays
 * a and b.  a gets the old state of the text, b gets the new state
 * The control char from the hunk is saved when inserting into a, but not b
 * (for performance while deleting files)
 */
static PyObject *
addlines(PyObject *self, PyObject *args)
{

	PyObject *fp, *hunk, *a, *b, *x;
	Py_ssize_t i;
	Py_ssize_t lena, lenb;
	Py_ssize_t num;
	Py_ssize_t todoa, todob;
	char *s, c;
	PyObject *l;
	if (!PyArg_ParseTuple(args, addlines_format,
			      &fp, &hunk, &lena, &lenb, &a, &b))
		return NULL;

	while (1) {
		todoa = lena - PyList_Size(a);
		todob = lenb - PyList_Size(b);
		num = todoa > todob ? todoa : todob;
		if (num == 0)
		    break;
		for (i = 0; i < num; i++) {
			x = PyFile_GetLine(fp, 0);
			s = PyBytes_AsString(x);
			c = *s;
			if (strcmp(s, "\\ No newline at end of file\n") == 0) {
				_fix_newline(hunk, a, b);
				continue;
			}
			if (c == '\n') {
				/* Some patches may be missing the control char
				 * on empty lines. Supply a leading space. */
				Py_DECREF(x);
				x = PyBytes_FromString(" \n");
			}
			PyList_Append(hunk, x);
			if (c == '+') {
				l = PyBytes_FromString(s + 1);
				PyList_Append(b, l);
				Py_DECREF(l);
			} else if (c == '-') {
				PyList_Append(a, x);
			} else {
				l = PyBytes_FromString(s + 1);
				PyList_Append(b, l);
				Py_DECREF(l);
				PyList_Append(a, x);
			}
			Py_DECREF(x);
		}
	}
	return Py_BuildValue("l", 0);
}

/*
 * compare the lines in a with the lines in b.  a is assumed to have
 * a control char at the start of each line, this char is ignored in the
 * compare
 */
static PyObject *
testhunk(PyObject *self, PyObject *args)
{

	PyObject *a, *b;
	long bstart;
	Py_ssize_t alen, blen;
	Py_ssize_t i;
	char *sa, *sb;

	if (!PyArg_ParseTuple(args, "OOl", &a, &b, &bstart))
		return NULL;
	alen = PyList_Size(a);
	blen = PyList_Size(b);
	if (alen > blen - bstart || bstart < 0) {
		return Py_BuildValue("l", -1);
	}
	for (i = 0; i < alen; i++) {
		sa = PyBytes_AsString(PyList_GET_ITEM(a, i));
		sb = PyBytes_AsString(PyList_GET_ITEM(b, i + bstart));
		if (strcmp(sa + 1, sb) != 0)
			return Py_BuildValue("l", -1);
	}
	return Py_BuildValue("l", 0);
}

static PyMethodDef methods[] = {
	{"addlines", addlines, METH_VARARGS, "add lines to a hunk\n"},
	{"fix_newline", fix_newline, METH_VARARGS, "fixup newline counters\n"},
	{"testhunk", testhunk, METH_VARARGS, "test lines in a hunk\n"},
	{NULL, NULL}
};

#ifdef IS_PY3K
static struct PyModuleDef diffhelpers_module = {
	PyModuleDef_HEAD_INIT,
	"diffhelpers",
	diffhelpers_doc,
	-1,
	methods
};

PyMODINIT_FUNC PyInit_diffhelpers(void)
{
	PyObject *m;

	m = PyModule_Create(&diffhelpers_module);
	if (m == NULL)
		return NULL;

	diffhelpers_Error = PyErr_NewException("diffhelpers.diffhelpersError",
											NULL, NULL);
	Py_INCREF(diffhelpers_Error);
	PyModule_AddObject(m, "diffhelpersError", diffhelpers_Error);

	return m;
}
#else
PyMODINIT_FUNC
initdiffhelpers(void)
{
	Py_InitModule3("diffhelpers", methods, diffhelpers_doc);
	diffhelpers_Error = PyErr_NewException("diffhelpers.diffhelpersError",
	                                        NULL, NULL);
}
#endif