--- parser3/src/main/untaint.C 2002/08/01 11:26:51 1.103 +++ parser3/src/main/untaint.C 2003/04/18 10:12:05 1.116 @@ -1,11 +1,11 @@ /** @file Parser: String class part: untaint mechanizm. - Copyright(c) 2001, 2002 ArtLebedev Group (http://www.artlebedev.com) + Copyright(c) 2001, 2003 ArtLebedev Group (http://www.artlebedev.com) Author: Alexandr Petrosian (http://paf.design.ru) */ -static const char* IDENT_UNTAINT_C="$Id: untaint.C,v 1.103 2002/08/01 11:26:51 paf Exp $"; +static const char* IDENT_UNTAINT_C="$Date: 2003/04/18 10:12:05 $"; #include "pa_pool.h" #include "pa_string.h" @@ -47,20 +47,14 @@ ulong string_string_shortcut_economy=0; dest+=bsize; \ inline bool need_file_encode(unsigned char c){ - // theoretical problem with, for instance, "_2B" and "." fragments, - // they would yield the same - // because need_file_encode('_')=false - // but we need to delete such files somehow, getting names from ^index - - if((c>='0') &&(c<='9') ||(c>='A') &&(c<='Z') ||(c>='a') &&(c<='z')) - return false; - - return !strchr( - " _./()-" -#ifdef WIN32 - ":\\~" + // russian letters and space ENABLED + // encoding only these... + return strchr( + "*?'\"<>|" +#ifndef WIN32 + ":\\" #endif - , c); + , c)!=0; } inline bool need_uri_encode(unsigned char c){ if((c>='0') &&(c<='9') ||(c>='A') &&(c<='Z') ||(c>='a') &&(c<='z')) @@ -290,10 +284,18 @@ size_t String::cstr_bufsize(Untaint_lang case UL_MAIL_HEADER: // tainted, untaint language: mail-header if(buf_charset) { + int parts_count=1; + const char *prev=row->item.ptr; + size_t size=row->item.size; + while(const char *comma_at=(const char*)memchr(prev, ',', size)) { + parts_count++; + size-=comma_at-prev; + prev=comma_at+1; + } // Subject: Re: parser3: =?koi8-r?Q?=D3=C5=CD=C9=CE=C1=D2?= dest+= row->item.size*3+ - buf_charset->name().size()+MAX_STRING/* worst: =?charset?Q?=%XX?= */; + parts_count*(buf_charset->name().size()+MAX_STRING/* worst: =?charset?Q?=%XX?= */); } else dest+=row->item.size; break; @@ -338,6 +340,39 @@ size_t String::cstr_bufsize(Untaint_lang return dest; } +/** http://www.ietf.org/rfc/rfc2047.txt +RFC +(3) As a replacement for a 'word' entity within a 'phrase', for example, + one that precedes an address in a From, To, or Cc header. The ABNF + definition for 'phrase' from RFC 822 thus becomes: + + phrase = 1*( encoded-word / word ) + + In this case the set of characters that may be used in a "Q"-encoded + 'encoded-word' is restricted to: . An 'encoded-word' that appears within a + 'phrase' MUST be separated from any adjacent 'word', 'text' or + 'special' by 'linear-white-space'. +... + (2) The 8-bit hexadecimal value 20 (e.g., ISO-8859-1 SPACE) may be + represented as "_" (underscore, ASCII 95.). (This character may + not pass through some internetwork mail gateways, but its use + will greatly enhance readability of "Q" encoded data with mail + readers that do not support this encoding.) Note that the "_" + always represents hexadecimal 20, even if the SPACE character + occupies a different code position in the character set in use. + + paf: obviously, + without "=", or one could not differ "=E0" and "russian letter a" + and without "_", or in would mean 0x20 +*/ +static bool mail_header_char_valid_within_Qencoded(char c) { + return c>='A' && c<='Z' + || c>='a' && c<='Z' + || c>='0' && c<='9' + || strchr("!*+-/", c); +} char *String::store_to(char *dest, Untaint_lang lang, SQL_Connection *connection, Charset *store_to_charset, @@ -345,7 +380,19 @@ char *String::store_to(char *dest, Untai // WARNING: // before any changes check cstr_bufsize first!!! bool whitespace=true; - STRING_FOREACH_ROW( +//debug + const Chunk *chunk=&(*this).head.chunk; \ + const Chunk::Row *row=chunk->rows; \ + uint countdown=chunk->count; \ + while(row!=(*this).append_here) { \ + if(countdown==0) { \ + chunk=row->link; \ + row=chunk->rows; \ + countdown=chunk->count; \ + }; +//*/ +// STRING_FOREACH_ROW( + uchar to_lang=lang==UL_UNSPECIFIED?row->item.lang:lang; char *start=dest; @@ -367,7 +414,12 @@ char *String::store_to(char *dest, Untai case UL_FILE_SPEC: // tainted, untaint language: file [name] escape( - encode(need_file_encode, '_'); + // Macintosh has problems with small Russian letter 'r' + if( *src=='\xF0' && pool().get_source_charset().name()=="windows-1251" ) { + // fixing that letter for most common charset + to_char('p'); + } else // fallback to default + encode(need_file_encode, '_'); ); break; case UL_URI: @@ -380,21 +432,18 @@ char *String::store_to(char *dest, Untai { const char *src=(const char *)client_ptr; for(int size=client_size; size--; src++) - switch(*src) { - case ' ': to_char('+'); break; - default: encode(need_uri_encode, '%'); - }; + encode(need_uri_encode, '%'); } break; case UL_HTTP_HEADER: // tainted, untaint language: http-field-content-text - escape(switch(*src) { - case ' ': to_char('+'); break; - default: encode(need_uri_encode, '%'); - }); + escape( + encode(need_uri_encode, '%'); + ); break; case UL_MAIL_HEADER: // tainted, untaint language: mail-header + // http://www.ietf.org/rfc/rfc2047.txt if(store_to_charset && store_to_charset_name) { const void *mail_ptr; size_t mail_size; @@ -405,18 +454,32 @@ char *String::store_to(char *dest, Untai // Subject: Re: parser3: =?koi8-r?Q?=D3=C5=CD=C9=CE=C1=D2?= const char *src=(const char *)mail_ptr; bool to_quoted_printable=false; - for(int size=mail_size; size--; src++) { - if((*src & 0x80) // starting quote-printable-encoding on first 8bit char - || (to_quoted_printable && (*src=='?' || *src=='=')) // additionally encoding '?' and '|' - ) { + + bool email=false; + for(const char *end=src+mail_size; src') + email=false; } if(to_quoted_printable) // close dest+=sprintf(dest, "?="); @@ -476,7 +539,7 @@ char *String::store_to(char *dest, Untai throw Exception(0, this, "unknown untaint language #%d", - static_cast(row->item.lang)); // sould never + static_cast(to_lang)); // should never break; // never } @@ -498,9 +561,13 @@ char *String::store_to(char *dest, Untai break; }; } else // piece without optimization +//debug whitespace=false; + row++; countdown--; \ + } +/* ); - +*/ return dest; }