From 5166266bf624c0a4d94d7751bb819c26cc1cc22d Mon Sep 17 00:00:00 2001 From: Francois Fleuret Date: Sun, 27 Jan 2013 21:19:48 +0100 Subject: [PATCH] Starting to write the search. --- mymail.c | 129 ++++++++++++++++++++++++++++++++++++++----------------- 1 file changed, 89 insertions(+), 40 deletions(-) diff --git a/mymail.c b/mymail.c index dc7c58c..25121a4 100644 --- a/mymail.c +++ b/mymail.c @@ -40,10 +40,12 @@ struct parsable_field { char *name; char *regexp_string; regex_t regexp; - FILE *db_file; }; -char *db_filename_prefix; +char *db_filename; +char *search_pattern; + +int action_index; /********************************************************************/ @@ -70,10 +72,11 @@ void usage(FILE *out) { } void read_file(const char *input_filename, - int nb_fields_to_parse, struct parsable_field *fields_to_parse) { + int nb_fields_to_parse, struct parsable_field *fields_to_parse, + FILE *db_file) { char raw_line[BUFFER_SIZE]; FILE *file; - int in_header; + int in_header, new_header; unsigned int position_in_file; file = fopen(input_filename, "r"); @@ -84,6 +87,7 @@ void read_file(const char *input_filename, } in_header = 0; + new_header = 0; position_in_file = 0; @@ -97,23 +101,28 @@ void read_file(const char *input_filename, exit(EXIT_FAILURE); } in_header = 1; + new_header = 1; } else if(strncmp(raw_line, "\n", 1) == 0) { if(in_header) { in_header = 0; } } /* if(in_header) { */ - /* printf("LINE.H %s", raw_line); */ + /* printf("LINE.H %s", raw_line); */ /* } else { */ - /* printf("LINE.B %s", raw_line); */ + /* printf("LINE.B %s", raw_line); */ /* } */ if(in_header) { int f; regmatch_t matches; + if(new_header) { + fprintf(db_file, "mail %s:%d\n", input_filename, position_in_file); + new_header = 0; + } for(f = 0; f < nb_fields_to_parse; f++) { if(regexec(&fields_to_parse[f].regexp, raw_line, 1, &matches, 0) == 0) { - fprintf(fields_to_parse[f].db_file, "%s:%d %s", - input_filename, position_in_file, + fprintf(db_file, "%s %s", + fields_to_parse[f].name, raw_line + matches.rm_eo); } } @@ -133,7 +142,8 @@ int ignore_entry(const char *name) { } void process_entry(const char *dir_name, - int nb_fields_to_parse, struct parsable_field *fields_to_parse) { + int nb_fields_to_parse, struct parsable_field *fields_to_parse, + FILE *db_file) { DIR *dir; struct dirent *dir_e; struct stat sb; @@ -159,14 +169,14 @@ void process_entry(const char *dir_name, while((dir_e = readdir(dir))) { if(!ignore_entry(dir_e->d_name)) { snprintf(subname, PATH_MAX, "%s/%s", dir_name, dir_e->d_name); - process_entry(subname, nb_fields_to_parse, fields_to_parse); + process_entry(subname, nb_fields_to_parse, fields_to_parse, db_file); } } closedir(dir); } else { if(S_ISREG(sb.st_mode)) { /* printf("Processing regular file '%s'.\n", dir_name); */ - read_file(dir_name, nb_fields_to_parse, fields_to_parse); + read_file(dir_name, nb_fields_to_parse, fields_to_parse, db_file); } } } @@ -183,20 +193,22 @@ enum static struct option long_options[] = { { "help", no_argument, 0, 'h' }, { "db-prefix", 1, 0, 'p' }, + { "search-pattern", 1, 0, 's' }, + { "index", 0, 0, 'i' }, { 0, 0, 0, 0 } }; static struct parsable_field fields_to_parse[] = { { "from", - "^[Ff][Rr][Oo][Mm]: *", - { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 }, 0 + "^\\([Ff][Rr][Oo][Mm]:\\|From\\) *", + { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 } }, { "dest", "^\\([Tt][Oo]\\|[Cc][Cc]\\|[Bb][Cc][Cc]\\): *", - { 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 } }, }; @@ -206,9 +218,12 @@ int main(int argc, char **argv) { char c; int f; + action_index = 0; + search_pattern = 0; + setlocale(LC_ALL, ""); - while ((c = getopt_long(argc, argv, "hp:", + while ((c = getopt_long(argc, argv, "hip:s:", long_options, NULL)) != -1) { switch(c) { @@ -217,8 +232,21 @@ int main(int argc, char **argv) { show_help = 1; break; + case 'i': + action_index = 1; + break; + case 'p': - db_filename_prefix = strdup(optarg); + db_filename = strdup(optarg); + break; + + case 's': + if(search_pattern) { + fprintf(stderr, + "mymail: Search pattern already defined.\n"); + exit(EXIT_FAILURE); + } + search_pattern = strdup(optarg); break; default: @@ -227,8 +255,8 @@ int main(int argc, char **argv) { } } - if(!db_filename_prefix) { - db_filename_prefix = strdup("/tmp/mymail_"); + if(!db_filename) { + db_filename = strdup("/tmp/mymail"); } if(error) { @@ -241,11 +269,9 @@ int main(int argc, char **argv) { exit(EXIT_SUCCESS); } - for(f = 0; f < nb_fields_to_parse; f++) { - char db_filename[BUFFER_SIZE]; - sprintf(db_filename, "%s%s", db_filename_prefix, fields_to_parse[f].name); - fields_to_parse[f].db_file = fopen(db_filename, "w"); - if(!fields_to_parse[f].db_file) { + if(action_index) { + FILE *db_file = fopen(db_filename, "w"); + if(!db_file) { fprintf(stderr, "mymail: Can not open \"%s\" for writing: %s\n", db_filename, @@ -253,28 +279,51 @@ int main(int argc, char **argv) { exit(EXIT_FAILURE); } - printf("Initialized %s.\n", db_filename); + for(f = 0; f < nb_fields_to_parse; f++) { + if(regcomp(&fields_to_parse[f].regexp, + fields_to_parse[f].regexp_string, + REG_ICASE)) { + fprintf(stderr, + "mymail: Syntax error in regexp \"%s\" for field \"%s\".\n", + fields_to_parse[f].regexp_string, + fields_to_parse[f].name); + exit(EXIT_FAILURE); + } + } - if(regcomp(&fields_to_parse[f].regexp, - fields_to_parse[f].regexp_string, - REG_ICASE)) { - fprintf(stderr, - "mymail: Syntax error in regexp \"%s\" for field \"%s\".\n", - fields_to_parse[f].regexp_string, - fields_to_parse[f].name); - exit(EXIT_FAILURE); + while(optind < argc) { + process_entry(argv[optind], + nb_fields_to_parse, fields_to_parse, db_file); + optind++; } - } - while(optind < argc) { - process_entry(argv[optind], - nb_fields_to_parse, fields_to_parse); - optind++; + fclose(db_file); + + for(f = 0; f < nb_fields_to_parse; f++) { + regfree(&fields_to_parse[f].regexp); + } } - for(f = 0; f < nb_fields_to_parse; f++) { - fclose(fields_to_parse[f].db_file); - regfree(&fields_to_parse[f].regexp); + else { + if(search_pattern) { + char *search_name; + char *search_regexp; + search_name = search_pattern; + search_regexp = search_pattern; + while(*search_regexp && *search_regexp != ' ') search_regexp++; + *search_regexp = '\0'; search_regexp++; + while(*search_regexp && *search_regexp == ' ') search_regexp++; + if(!*search_regexp) { + fprintf(stderr, + "Syntax error in the search pattern.\n"); + exit(EXIT_FAILURE); + } + printf("Starting search in %s for field \"%s\" matching \"%s\".\n", + db_filename, + search_name, + search_regexp); + free(search_pattern); + } } exit(EXIT_SUCCESS); -- 2.20.1