changeset 36184:29dd37a418aa

bdiff: write a native version of splitnewlines

./hg perfunidiff mercurial/manifest.py 0 --count 500 --profile before:
! wall 0.309280 comb 0.350000 user 0.290000 sys 0.060000 (best of 32)

./hg perfunidiff mercurial/manifest.py 0 --count 500 --profile after:
! wall 0.241572 comb 0.260000 user 0.240000 sys 0.020000 (best of 39)

so it's about 20% faster. I hate Python. I wish we could usefully
write this in Rust, but it doesn't look like that's realistic without
using the cpython crate, which I'd still like to avoid.

Differential Revision: https://phab.mercurial-scm.org/D1973

--- a/mercurial/cext/bdiff.c	Mon Feb 12 16:09:31 2018 +0100
+++ b/mercurial/cext/bdiff.c	Thu Jan 25 21:16:28 2018 -0500
@@ -180,16 +180,66 @@
 	return result ? result : PyErr_NoMemory();
 }
 
+static bool sliceintolist(PyObject *list, Py_ssize_t destidx,
+                          const char *source, Py_ssize_t len)
+{
+	PyObject *sliced = PyBytes_FromStringAndSize(source, len);
+	if (sliced == NULL)
+		return false;
+	PyList_SET_ITEM(list, destidx, sliced);
+	return true;
+}
+
+static PyObject *splitnewlines(PyObject *self, PyObject *args)
+{
+	const char *text;
+	Py_ssize_t nelts = 0, size, i, start = 0;
+	PyObject *result = NULL;
+
+	if (!PyArg_ParseTuple(args, "s#", &text, &size)) {
+		goto abort;
+	}
+	if (!size) {
+		return PyList_New(0);
+	}
+	/* This loops to size-1 because if the last byte is a newline,
+	 * we don't want to perform a split there. */
+	for (i = 0; i < size - 1; ++i) {
+		if (text[i] == '\n') {
+			++nelts;
+		}
+	}
+	if ((result = PyList_New(nelts + 1)) == NULL)
+		goto abort;
+	nelts = 0;
+	for (i = 0; i < size - 1; ++i) {
+		if (text[i] == '\n') {
+			if (!sliceintolist(result, nelts++, text + start,
+			                   i - start + 1))
+				goto abort;
+			start = i + 1;
+		}
+	}
+	if (!sliceintolist(result, nelts++, text + start, size - start))
+		goto abort;
+	return result;
+abort:
+	Py_XDECREF(result);
+	return NULL;
+}
+
 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"},
+    {"splitnewlines", splitnewlines, METH_VARARGS,
+     "like str.splitlines, but only split on newlines\n"},
     {NULL, NULL},
 };
 
-static const int version = 1;
+static const int version = 2;
 
 #ifdef IS_PY3K
 static struct PyModuleDef bdiff_module = {

--- a/mercurial/mdiff.py	Mon Feb 12 16:09:31 2018 +0100
+++ b/mercurial/mdiff.py	Thu Jan 25 21:16:28 2018 -0500
@@ -29,16 +29,7 @@
 patches = mpatch.patches
 patchedsize = mpatch.patchedsize
 textdiff = bdiff.bdiff
-
-def splitnewlines(text):
-    '''like str.splitlines, but only split on newlines.'''
-    lines = [l + '\n' for l in text.split('\n')]
-    if lines:
-        if lines[-1] == '\n':
-            lines.pop()
-        else:
-            lines[-1] = lines[-1][:-1]
-    return lines
+splitnewlines = bdiff.splitnewlines
 
 class diffopts(object):
     '''context is the number of context lines

--- a/mercurial/policy.py	Mon Feb 12 16:09:31 2018 +0100
+++ b/mercurial/policy.py	Thu Jan 25 21:16:28 2018 -0500
@@ -71,7 +71,7 @@
 # keep in sync with "version" in C modules
 _cextversions = {
     (r'cext', r'base85'): 1,
-    (r'cext', r'bdiff'): 1,
+    (r'cext', r'bdiff'): 2,
     (r'cext', r'diffhelpers'): 1,
     (r'cext', r'mpatch'): 1,
     (r'cext', r'osutil'): 3,

--- a/mercurial/pure/bdiff.py	Mon Feb 12 16:09:31 2018 +0100
+++ b/mercurial/pure/bdiff.py	Thu Jan 25 21:16:28 2018 -0500
@@ -90,3 +90,13 @@
         text = re.sub('[ \t\r]+', ' ', text)
         text = text.replace(' \n', '\n')
     return text
+
+def splitnewlines(text):
+    '''like str.splitlines, but only split on newlines.'''
+    lines = [l + '\n' for l in text.split('\n')]
+    if lines:
+        if lines[-1] == '\n':
+            lines.pop()
+        else:
+            lines[-1] = lines[-1][:-1]
+    return lines