upstream/mercurial-mirror Files · mercurial/cext/charencode.h

match: optimize matcher when all patterns are of rootfilesin kind...

match: optimize matcher when all patterns are of rootfilesin kind Internally at Google, we use narrowspecs with only rootfilesin-kind patterns. Sometimes there are thousands of such patterns (i.e. thousands of tracked directories). In such cases, it can take quite long to build and evaluate the resulting matcher. This patch optimizes matchers that have only patterns of rootfilesin so it instead of creating a regular expression, it matches the given file's directory against the set of directories. In a repo with ~3600 tracked directories, it takes about 1.35 s to build the matcher and 2.7 s to walk the dirstate before this patch. After, it takes 0.04 s to create the matcher and 0.87 s to walk the dirstate. It may be worthwhile to do similar optimizations for e.g. patterns of type "kind:", but that's not a priority for us right now. Differential Revision: https://phab.mercurial-scm.org/D5058

Augie Fackler - - Load All Authors

File last commit:

r36075:81199632 default


                r40278:19ed212d

default

Download file

             charencode.h
        
                    61 lines
            
             | 2.1 KiB
            
                | text/x-c
            
             |
                CLexer
            
             / mercurial / cext / charencode.h
          
                    History
                
                 |
                  Annotation
                 | Raw
                 |Copy content
                 |Copy permalink

      /*

       charencode.h - miscellaneous character encoding

       This software may be used and distributed according to the terms of

       the GNU General Public License, incorporated herein by reference.

      */

      #ifndef _HG_CHARENCODE_H_

      #define _HG_CHARENCODE_H_

      #include <Python.h>

      #include "compat.h"

      /* This should be kept in sync with normcasespecs in encoding.py. */

      enum normcase_spec {

      	NORMCASE_LOWER = -1,

      	NORMCASE_UPPER = 1,

      	NORMCASE_OTHER = 0

      };

      PyObject *unhexlify(const char *str, Py_ssize_t len);

      PyObject *isasciistr(PyObject *self, PyObject *args);

      PyObject *asciilower(PyObject *self, PyObject *args);

      PyObject *asciiupper(PyObject *self, PyObject *args);

      PyObject *make_file_foldmap(PyObject *self, PyObject *args);

      PyObject *jsonescapeu8fast(PyObject *self, PyObject *args);

      /* clang-format off */

      static const int8_t hextable[256] = {

      	-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,

      	-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,

      	-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,

      	 0,  1,  2,  3,  4,  5,  6,  7,  8,  9, -1, -1, -1, -1, -1, -1, /* 0-9 */

      	-1, 10, 11, 12, 13, 14, 15, -1, -1, -1, -1, -1, -1, -1, -1, -1, /* A-F */

      	-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,

      	-1, 10, 11, 12, 13, 14, 15, -1, -1, -1, -1, -1, -1, -1, -1, -1, /* a-f */

      	-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,

      	-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,

      	-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,

      	-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,

      	-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,

      	-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,

      	-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,

      	-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,

      	-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1

      };

      /* clang-format on */

      static inline int hexdigit(const char *p, Py_ssize_t off)

      {

      	int8_t val = hextable[(unsigned char)p[off]];

      	if (val >= 0) {

      		return val;

      	}

      	PyErr_SetString(PyExc_ValueError, "input contains non-hex character");

      	return 0;

      }

      #endif /* _HG_CHARENCODE_H_ */

	Site-wide shortcuts
/	Use quick search box
g h	Goto home page
g g	Goto my private gists page
g G	Goto my public gists page
g 0-9	Goto bookmarked items from 0-9
n r	New repository page
n g	New gist page

	Repositories
g s	Goto summary page
g c	Goto changelog page
g f	Goto files page
g F	Goto files page with file search activated
g p	Goto pull requests page
g o	Goto repository settings
g O	Goto repository access permissions settings
t s	Toggle sidebar on some pages

				/*
				charencode.h - miscellaneous character encoding

				This software may be used and distributed according to the terms of
				the GNU General Public License, incorporated herein by reference.
				*/

				#ifndef _HG_CHARENCODE_H_
				#define _HG_CHARENCODE_H_

				#include <Python.h>
				#include "compat.h"

				/* This should be kept in sync with normcasespecs in encoding.py. */
				enum normcase_spec {
				NORMCASE_LOWER = -1,
				NORMCASE_UPPER = 1,
				NORMCASE_OTHER = 0
				};

				PyObject unhexlify(const char str, Py_ssize_t len);
				PyObject isasciistr(PyObject self, PyObject *args);
				PyObject asciilower(PyObject self, PyObject *args);
				PyObject asciiupper(PyObject self, PyObject *args);
				PyObject make_file_foldmap(PyObject self, PyObject *args);
				PyObject jsonescapeu8fast(PyObject self, PyObject *args);

				/* clang-format off */
				static const int8_t hextable[256] = {
				-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
				-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
				-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
				0, 1, 2, 3, 4, 5, 6, 7, 8, 9, -1, -1, -1, -1, -1, -1, /* 0-9 */
				-1, 10, 11, 12, 13, 14, 15, -1, -1, -1, -1, -1, -1, -1, -1, -1, /* A-F */
				-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
				-1, 10, 11, 12, 13, 14, 15, -1, -1, -1, -1, -1, -1, -1, -1, -1, /* a-f */
				-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
				-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
				-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
				-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
				-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
				-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
				-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
				-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
				-1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1
				};
				/* clang-format on */

				static inline int hexdigit(const char *p, Py_ssize_t off)
				{
				int8_t val = hextable[(unsigned char)p[off]];

				if (val >= 0) {
				return val;
				}

				PyErr_SetString(PyExc_ValueError, "input contains non-hex character");
				return 0;
				}

				#endif /* _HG_CHARENCODE_H_ */