From 62ea7ff4f96245390d05e16a61dc78b15cf54b4b Mon Sep 17 00:00:00 2001 From: david Date: Sun, 25 Nov 2012 17:20:01 +2000 Subject: [PATCH] [Patch v2 01/17] hex-escape: (en|de)code strings to/from restricted character set --- 3e/d0feca07b59f6303c12ff8076f10d659b97938 | 306 ++++++++++++++++++++++ 1 file changed, 306 insertions(+) create mode 100644 3e/d0feca07b59f6303c12ff8076f10d659b97938 diff --git a/3e/d0feca07b59f6303c12ff8076f10d659b97938 b/3e/d0feca07b59f6303c12ff8076f10d659b97938 new file mode 100644 index 000000000..90575140a --- /dev/null +++ b/3e/d0feca07b59f6303c12ff8076f10d659b97938 @@ -0,0 +1,306 @@ +Return-Path: +X-Original-To: notmuch@notmuchmail.org +Delivered-To: notmuch@notmuchmail.org +Received: from localhost (localhost [127.0.0.1]) + by olra.theworths.org (Postfix) with ESMTP id C506F429E28 + for ; Sat, 24 Nov 2012 13:20:34 -0800 (PST) +X-Virus-Scanned: Debian amavisd-new at olra.theworths.org +X-Spam-Flag: NO +X-Spam-Score: 0 +X-Spam-Level: +X-Spam-Status: No, score=0 tagged_above=-999 required=5 tests=[none] + autolearn=disabled +Received: from olra.theworths.org ([127.0.0.1]) + by localhost (olra.theworths.org [127.0.0.1]) (amavisd-new, port 10024) + with ESMTP id DVGi8InkTr9r for ; + Sat, 24 Nov 2012 13:20:32 -0800 (PST) +Received: from tesseract.cs.unb.ca (tesseract.cs.unb.ca [131.202.240.238]) + (using TLSv1 with cipher AES256-SHA (256/256 bits)) + (No client certificate requested) + by olra.theworths.org (Postfix) with ESMTPS id 8AF1B431FAF + for ; Sat, 24 Nov 2012 13:20:32 -0800 (PST) +Received: from fctnnbsc30w-156034089108.dhcp-dynamic.fibreop.nb.bellaliant.net + ([156.34.89.108] helo=zancas.localnet) + by tesseract.cs.unb.ca with esmtpsa + (TLS1.0:DHE_RSA_AES_128_CBC_SHA1:16) (Exim 4.72) + (envelope-from ) + id 1TcN9L-0006SH-58; Sat, 24 Nov 2012 17:20:31 -0400 +Received: from bremner by zancas.localnet with local (Exim 4.80) + (envelope-from ) + id 1TcN9F-0008CQ-Md; Sat, 24 Nov 2012 17:20:25 -0400 +From: david@tethera.net +To: notmuch@notmuchmail.org +Subject: [Patch v2 01/17] hex-escape: (en|de)code strings to/from restricted + character set +Date: Sat, 24 Nov 2012 17:20:01 -0400 +Message-Id: <1353792017-31459-2-git-send-email-david@tethera.net> +X-Mailer: git-send-email 1.7.10.4 +In-Reply-To: <1353792017-31459-1-git-send-email-david@tethera.net> +References: <1353792017-31459-1-git-send-email-david@tethera.net> +X-Spam_bar: - +Cc: David Bremner +X-BeenThere: notmuch@notmuchmail.org +X-Mailman-Version: 2.1.13 +Precedence: list +List-Id: "Use and development of the notmuch mail system." + +List-Unsubscribe: , + +List-Archive: +List-Post: +List-Help: +List-Subscribe: , + +X-List-Received-Date: Sat, 24 Nov 2012 21:20:35 -0000 + +From: David Bremner + +The character set is chosen to be suitable for pathnames, and the same +as that used by contrib/nmbug + +[With additions by Jani Nikula] +--- + util/Makefile.local | 2 +- + util/hex-escape.c | 168 +++++++++++++++++++++++++++++++++++++++++++++++++++ + util/hex-escape.h | 41 +++++++++++++ + 3 files changed, 210 insertions(+), 1 deletion(-) + create mode 100644 util/hex-escape.c + create mode 100644 util/hex-escape.h + +diff --git a/util/Makefile.local b/util/Makefile.local +index c7cae61..3ca623e 100644 +--- a/util/Makefile.local ++++ b/util/Makefile.local +@@ -3,7 +3,7 @@ + dir := util + extra_cflags += -I$(srcdir)/$(dir) + +-libutil_c_srcs := $(dir)/xutil.c $(dir)/error_util.c ++libutil_c_srcs := $(dir)/xutil.c $(dir)/error_util.c $(dir)/hex-escape.c + + libutil_modules := $(libutil_c_srcs:.c=.o) + +diff --git a/util/hex-escape.c b/util/hex-escape.c +new file mode 100644 +index 0000000..d8905d0 +--- /dev/null ++++ b/util/hex-escape.c +@@ -0,0 +1,168 @@ ++/* hex-escape.c - Manage encoding and decoding of byte strings into path names ++ * ++ * Copyright (c) 2011 David Bremner ++ * ++ * This program is free software: you can redistribute it and/or modify ++ * it under the terms of the GNU General Public License as published by ++ * the Free Software Foundation, either version 3 of the License, or ++ * (at your option) any later version. ++ * ++ * This program is distributed in the hope that it will be useful, ++ * but WITHOUT ANY WARRANTY; without even the implied warranty of ++ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the ++ * GNU General Public License for more details. ++ * ++ * You should have received a copy of the GNU General Public License ++ * along with this program. If not, see http://www.gnu.org/licenses/ . ++ * ++ * Author: David Bremner ++ */ ++ ++#include ++#include ++#include ++#include ++#include "error_util.h" ++#include "hex-escape.h" ++ ++static const size_t default_buf_size = 1024; ++ ++static const char *output_charset = ++ "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+-_@=.:,"; ++ ++static const char escape_char = '%'; ++ ++static int ++is_output (char c) ++{ ++ return (strchr (output_charset, c) != NULL); ++} ++ ++static int ++maybe_realloc (void *ctx, size_t needed, char **out, size_t *out_size) ++{ ++ if (*out_size < needed) { ++ ++ if (*out == NULL) ++ *out = talloc_size (ctx, needed); ++ else ++ *out = talloc_realloc (ctx, *out, char, needed); ++ ++ if (*out == NULL) ++ return 0; ++ ++ *out_size = needed; ++ } ++ return 1; ++} ++ ++hex_status_t ++hex_encode (void *ctx, const char *in, char **out, size_t *out_size) ++{ ++ ++ const unsigned char *p; ++ char *q; ++ ++ size_t escape_count = 0; ++ size_t len = 0; ++ size_t needed; ++ ++ assert (ctx); assert (in); assert (out); assert (out_size); ++ ++ for (p = (unsigned char *) in; *p; p++) { ++ escape_count += (!is_output (*p)); ++ len++; ++ } ++ ++ needed = len + escape_count * 2 + 1; ++ ++ if (*out == NULL) ++ *out_size = 0; ++ ++ if (!maybe_realloc (ctx, needed, out, out_size)) ++ return HEX_OUT_OF_MEMORY; ++ ++ q = *out; ++ p = (unsigned char *) in; ++ ++ while (*p) { ++ if (is_output (*p)) { ++ *q++ = *p++; ++ } else { ++ sprintf (q, "%%%02x", *p++); ++ q += 3; ++ } ++ } ++ ++ *q = '\0'; ++ return HEX_SUCCESS; ++} ++ ++/* Hex decode 'in' to 'out'. ++ * ++ * This must succeed for in == out to support hex_decode_inplace(). ++ */ ++static hex_status_t ++hex_decode_internal (const char *in, unsigned char *out) ++{ ++ char buf[3]; ++ ++ while (*in) { ++ if (*in == escape_char) { ++ char *endp; ++ ++ /* This also handles unexpected end-of-string. */ ++ if (!isxdigit ((unsigned char) in[1]) || ++ !isxdigit ((unsigned char) in[2])) ++ return HEX_SYNTAX_ERROR; ++ ++ buf[0] = in[1]; ++ buf[1] = in[2]; ++ buf[2] = '\0'; ++ ++ *out = strtoul (buf, &endp, 16); ++ ++ if (endp != buf + 2) ++ return HEX_SYNTAX_ERROR; ++ ++ in += 3; ++ out++; ++ } else { ++ *out++ = *in++; ++ } ++ } ++ ++ *out = '\0'; ++ ++ return HEX_SUCCESS; ++} ++ ++hex_status_t ++hex_decode_inplace (char *s) ++{ ++ /* A decoded string is never longer than the encoded one, so it is ++ * safe to decode a string onto itself. */ ++ return hex_decode_internal (s, (unsigned char *) s); ++} ++ ++hex_status_t ++hex_decode (void *ctx, const char *in, char **out, size_t * out_size) ++{ ++ const char *p; ++ size_t escape_count = 0; ++ size_t needed = 0; ++ ++ assert (ctx); assert (in); assert (out); assert (out_size); ++ ++ size_t len = strlen (in); ++ ++ for (p = in; *p; p++) ++ escape_count += (*p == escape_char); ++ ++ needed = len - escape_count * 2 + 1; ++ ++ if (!maybe_realloc (ctx, needed, out, out_size)) ++ return HEX_OUT_OF_MEMORY; ++ ++ return hex_decode_internal (in, (unsigned char *) *out); ++} +diff --git a/util/hex-escape.h b/util/hex-escape.h +new file mode 100644 +index 0000000..5182042 +--- /dev/null ++++ b/util/hex-escape.h +@@ -0,0 +1,41 @@ ++#ifndef _HEX_ESCAPE_H ++#define _HEX_ESCAPE_H ++ ++typedef enum hex_status { ++ HEX_SUCCESS = 0, ++ HEX_SYNTAX_ERROR, ++ HEX_OUT_OF_MEMORY ++} hex_status_t; ++ ++/* ++ * The API for hex_encode() and hex_decode() is modelled on that for ++ * getline. ++ * ++ * If 'out' points to a NULL pointer a char array of the appropriate ++ * size is allocated using talloc, and out_size is updated. ++ * ++ * If 'out' points to a non-NULL pointer, it assumed to describe an ++ * existing char array, with the size given in *out_size. This array ++ * may be resized by talloc_realloc if needed; in this case *out_size ++ * will also be updated. ++ * ++ * Note that it is an error to pass a NULL pointer for any parameter ++ * of these routines. ++ */ ++ ++hex_status_t ++hex_encode (void *talloc_ctx, const char *in, char **out, ++ size_t *out_size); ++ ++hex_status_t ++hex_decode (void *talloc_ctx, const char *in, char **out, ++ size_t *out_size); ++ ++/* ++ * Non-allocating hex decode to decode 's' in-place. The length of the ++ * result is always equal to or shorter than the length of the ++ * original. ++ */ ++hex_status_t ++hex_decode_inplace (char *s); ++#endif +-- +1.7.10.4 + -- 2.26.2