[PATCH 1 of 7 V4] sparse-revlog: add a `index_get_start` function in C

[Boris Feld]

# HG changeset patch
# User Boris Feld <boris.feld at octobus.net>
# Date 1542725358 0
#      Tue Nov 20 14:49:18 2018 +0000
# Node ID 60a55da39befa4996c1a88ca6f663765ea143ef2
# Parent  337a389953366f059f2cb88129031ba3e67e0bbc
# EXP-Topic sparse-perf
# Available At https://bitbucket.org/octobus/mercurial-devel/
#              hg pull https://bitbucket.org/octobus/mercurial-devel/ -r 60a55da39bef
sparse-revlog: add a `index_get_start` function in C

We are about to implement a native version of `slicechunktodensity`. For
clarity, we introduce the helper functions first. This new function provides
an efficient way to retrieve some of the information needed by
`slicechunktodensity`.

diff --git a/mercurial/cext/revlog.c b/mercurial/cext/revlog.c
--- a/mercurial/cext/revlog.c
+++ b/mercurial/cext/revlog.c
@@ -185,6 +185,46 @@ static inline int index_get_parents(inde
 	return 0;
 }
 
+static inline int64_t index_get_start(indexObject *self, Py_ssize_t rev)
+{
+	uint64_t offset;
+	if (rev >= self->length) {
+		PyObject *tuple;
+		PyObject *pylong;
+		unsigned PY_LONG_LONG tmp;
+		tuple = PyList_GET_ITEM(self->added, rev - self->length);
+		pylong = PyTuple_GET_ITEM(tuple, 0);
+#ifndef IS_PY3K
+		if (PyInt_Check(pylong)) {
+			long tmp2 = PyInt_AsLong(pylong);
+			if (tmp2 < 0) {
+				return -1;
+			}
+			tmp = (unsigned PY_LONG_LONG)tmp2;
+		} else {
+#endif
+			tmp = PyLong_AsUnsignedLongLong(pylong);
+			if (tmp == (unsigned PY_LONG_LONG) - 1) {
+				return -1;
+			}
+
+#ifndef IS_PY3K
+		}
+#endif
+		offset = (uint64_t)tmp;
+	} else {
+		const char *data = index_deref(self, rev);
+		offset = getbe32(data + 4);
+		if (rev == 0) /* mask out version number for the first entry */
+			offset &= 0xFFFF;
+		else {
+			uint32_t offset_high = getbe32(data);
+			offset |= ((uint64_t)offset_high) << 32;
+		}
+	}
+	return (int64_t)(offset >> 16);
+}
+
 /*
  * RevlogNG format (all in big endian, data may be inlined):
  *    6 bytes: offset