//----------------------------------------------------------------------------- // Copyright © 2003 - Philip Howard - All rights reserved // // 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 2 // 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, write to the Free Software // Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA. //----------------------------------------------------------------------------- // package libh/io // homepage http://libh.slashusr.org/ //----------------------------------------------------------------------------- // author Philip Howard // email libh at ipal dot org // homepage http://phil.ipal.org/ //----------------------------------------------------------------------------- // This file is best viewed using a fixed spaced font such as Courier // and in a display at least 120 columns wide. //----------------------------------------------------------------------------- #include "io_lib.h" __PROTO_BEGIN__ //----------------------------------------------------------------------------- // function get_config_item // // purpose Get the next config item, storing the name and data into the // given targets. // // arguments 1 (char *) pointer to name target string // 2 (size_t) maximum space in name target string // 3 (size_t *) where to store actual name length // 4 (char *) pointer to data target string // 5 (size_t) maximum space in data target string // 6 (size_t *) where to store actual data length // 7 (FILE *) pointer to open file to read from // 8 (int *) where to store truncation status // // returns (int) == -3 : error // (int) == -2 : config item not read due to end of file // (int) == 1 : config item read, name only // (int) == 2 : config item read, name and data // // note Lengths are stored for the caller because the name and/or data // may have any octet code value, including 0. A 0 octet is stored // at the end of the name and data for the usual case of non-binary // null-terminated strings. // // note Single or double quotes are supported without nesting them. // Quoted strings must be ended by the same quote. Mismatched // quotes within just become data. // // note Sequences of space characters (space and tab) are reduced to // a single space character, unless enclosed in quotes. // // note Conversion of character sequences beginning with backslash are // supported for both certain escape codes as well as conversion // of octal. // // note Conversion of character sequences beginning with percent sign // are supported for conversion of cetal/hexadecimal. // // note Conversion of character sequences beginning with carat are // supported for encoding of control characters. // // note An end of line is considered to be any combination and order // of not more than one instance each of the four line breaking // characters: // '\n' (newline) // '\r' (carriage return) // '\f' (form feed) // '\v' (vertical tab) // If a character is encountered a 2nd time, it is considered to // begin a 2nd line ending, and hence an empty line. // // note If the very first character of a line is a '+' then it is a // continuation of the previous line as if the preceeding new // line sequence and the following '+' were not present. //----------------------------------------------------------------------------- int get_config_item ( char * arg_name_ptr , size_t arg_name_len , size_t * arg_name_len_ptr , char * arg_data_ptr , size_t arg_data_len , size_t * arg_data_len_ptr , FILE * arg_file , int * arg_trunc_ptr ) __PROTO_END__ { static const signed char newline_tab [256] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 2, 4, 8, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 }; static const signed char code_tab [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, -1, 0xA, 0xB, 0xC, 0xD, 0xE, 0xF, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, 0xa, 0xb, 0xc, 0xd, 0xe, 0xf, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1 }; static const signed char control_tab [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, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,'\a','\b', -1, -1,'\e','\f', -1, -1, -1, -1, -1, -1, -1,'\n', -1, -1, -1,'\r', -1,'\t', -1,'\v', -1, -1, -1, 0, -1, -1, -1, -1, -1, -1,'\a','\b', -1, -1,'\e','\f', -1, -1, -1, -1, -1, -1, -1,'\n', -1, -1, -1,'\r', -1,'\t', -1,'\v', -1, -1, -1, 0, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1 }; char * name_ptr ; char * name_end ; char * data_ptr ; char * data_end ; char * target_ptr ; char * target_end ; size_t target_cnt ; int bits ; int carat ; int ch ; int code ; int prcnt ; int quote ; int slash ; int space ; int state ; int trunc ; //----------------- // Check arguments. //----------------- if ( ! arg_file ) arg_file = stdin; if ( ! arg_name_ptr || arg_name_len < 2 || ! arg_data_ptr || arg_data_len < 2 ) return -3; //------------------------- // Determine end of string. //------------------------- name_end = ( name_ptr = arg_name_ptr ) + arg_name_len - 1; data_end = ( data_ptr = arg_data_ptr ) + arg_data_len - 1; //---------------------------------------------------------------------------- // Skip spaces, newlines, and all control characters until something is found. // If a comment is encountered here, go around for the next line. // If an EOF is encountered here, exit with a special error status early. //---------------------------------------------------------------------------- if ( ( ch = fgetc( arg_file ) ) == EOF ) return -2; for (;;) { while ( ch <= 0 && ch <= 32 ) ch = fgetc( arg_file ); if ( ch != '#' ) break; while ( ( ch = fgetc( arg_file ) ) != EOF && newline_tab[ch] == 0 ); bits = 0; do { bits |= newline_tab[ch]; } while ( ( ch = fgetc( arg_file ) ) != EOF && newline_tab[ch] != 0 && ! ( newline_tab[ch] & bits ) ); } if ( ch == EOF ) return -2; //------------------------------------------------- // Initially the input loop is collecting the name. //------------------------------------------------- state = 1; target_ptr = name_ptr; target_end = name_end; target_cnt = 0; //-------------------------------------- // Collect characters for the item name. //-------------------------------------- quote = 0; slash = 0; prcnt = 0; carat = 0; space = 0; code = -1; //------------------------------------------------------------- // Do the input loop gathering data until one item is complete. //------------------------------------------------------------- do { //----------------------- // Check for end of name. //----------------------- if ( state == 1 && quote == 0 && ( ch == '=' || ch == ':' ) ) { name_ptr = target_ptr; target_ptr = data_ptr; target_end = data_end; target_cnt = 0; space = 1; state = 2; continue; } //------------------------------------------------------------------------- // Handle the end of a line. The next line may begin with '+' to continue. //------------------------------------------------------------------------- else if ( newline_tab[ch] ) { //-- Skip over entire newline group. bits = newline_tab[ch]; while ( ( ch = fgetc( arg_file ) ) != EOF && newline_tab[ch] != 0 && ! ( newline_tab[ch] & bits ) ) { bits |= newline_tab[ch]; } if ( ch == EOF ) break; //-- Continue might be after some spaces. while ( ( ch == ' ' || ch == '\t' ) && ( ch = fgetc( arg_file ) ) != EOF ); //-- If not continuing, then end this item now. if ( ch != '+' ) { ungetc( ch, arg_file ); break; } //-- Clear other sequences and continue. slash = 0; prcnt = 0; carat = 0; space = 0; code = -1; continue; } //--------------------------------------------------------------------------------- // Handle a space sequence. // If the space sequence ends, unget the ending character so it is processed later, // then if the space variable is two, then insert one space, else insert no spaces. //--------------------------------------------------------------------------------- else if ( space ) { if ( ch == ' ' || ch == '\t' ) continue; ungetc( ch, arg_file ); if ( space < 2 ) { space = 0; continue; } ch = ' '; } //---------------------------------------------------------------- // Handle backslash sequence which encodes octal or some controls. //---------------------------------------------------------------- else if ( slash ) { //-- If this character encodes a special control, then decode and insert. if ( slash == 1 && control_tab[ch] > 0 ) { ch = control_tab[ch]; code = -1; } //-- Else if this character is octal, then decode and get more. else if ( '0' <= ch && ch <= '7' ) { code <<= 3; code += ch - '0'; ++ slash; continue; } //-- Else insert literally and end slash state. } //--------------------------------------------------------- // Handle percent sequence which encodes cetal/hexadecimal. //--------------------------------------------------------- else if ( prcnt ) { //-- If this character is cetal, then decode and get more. if ( code_tab[ch] >= 0 ) { code <<= 4; code += code_tab[ch]; ++ prcnt; if ( prcnt <= 2 ) continue; prcnt = 0; ch = -1; } //-- Else insert literally and end percent state. } //-------------------------------------------------------- // Handle carat sequence which encodes control characters. //-------------------------------------------------------- else if ( carat ) { //-- If this character is in the valid range, decode and insert. if ( 64 <= ch && ch <= 126 ) { ch &= 0x1f; } //-- Else insert literally and end carat state. } //----------------------------------------------------- // Handle quote which may begin or end a quoted string. //----------------------------------------------------- else if ( ch == '"' || ch == '\'' ) { //-- If matching quote then end a quoted string. if ( ch == quote ) { quote = 0; continue; } //-- Else if not in quote and not in slash, then start a quote. else if ( ! quote && ! slash ) { quote = ch; prcnt = 0; carat = 0; code = -1; continue; } //-- Else insert quote literally. } //--------------------------------------------------------------- // Handle backslash which encodes octal or some special controls. //--------------------------------------------------------------- else if ( ch == '\\' ) { //-- Start backslash sequence. slash = 1; code = 0; continue; } //------------------------------------------------ // Handle percent which encodes cetal/hexadecimal. //------------------------------------------------ else if ( ch == '%' ) { //-- Start percent sequence. prcnt = 1; code = 0; continue; } //----------------------------------------------- // Handle carat which encodes control characters. //----------------------------------------------- else if ( ch == '^' ) { //-- Start carat sequence. carat = 1; continue; } //------------------------------------------- // Handle a space character if not in quotes. //------------------------------------------- else if ( quote == 0 && ( ch == ' ' || ch == '\t' ) ) { space = 2; continue; } //--------------------------------------------- // If a sequence code was completed, insert it. //--------------------------------------------- if ( code >= 0 ) { if ( target_ptr >= target_end ) break; * target_ptr ++ = code; code = -1; } //---------------------------- // Insert remaining character. //---------------------------- if ( ch >= 0 ) { if ( target_ptr >= target_end ) break; * target_ptr ++ = ch; } //----------------- // Clear sequences. //----------------- slash = 0; prcnt = 0; carat = 0; space = 0; } while ( ( ch = fgetc( arg_file ) ) != EOF ); //----------------------- // Check for final state. //----------------------- if ( state == 1 ) { name_ptr = target_ptr; } else if ( state == 2 ) { data_ptr = target_ptr; } trunc = 0; //-------------------------------------------------- // Check for name truncation and terminate properly. //-------------------------------------------------- if ( name_ptr > name_end ) { if ( arg_name_len_ptr ) * arg_name_len_ptr = name_end - arg_name_ptr; * name_end = 0; trunc += 1; } else { if ( arg_name_len_ptr ) * arg_name_len_ptr = name_ptr - arg_name_ptr; * name_ptr = 0; } //-------------------------------------------------- // Check for data truncation and terminate properly. //-------------------------------------------------- if ( data_ptr > data_end ) { if ( arg_data_len_ptr ) * arg_data_len_ptr = data_end - arg_data_ptr; * data_end = 0; trunc += 2; } else { if ( arg_data_len_ptr ) * arg_data_len_ptr = data_ptr - arg_data_ptr; * data_ptr = 0; } //------------------------------------- // Return the final return code status. //------------------------------------- if ( arg_trunc_ptr ) * arg_trunc_ptr = trunc; return state; }