X-Git-Url: https://fleuret.org/cgi-bin/gitweb/gitweb.cgi?a=blobdiff_plain;f=finddup.c;h=983168b6feea2f0d17ff2e5720cf54421304c67b;hb=ef337e5e5c15540fe4f4f367a9bd4599b4559634;hp=7a20257d7b48d7baaddfbc7e3df6237a9151fc9a;hpb=557365f6f9347243c49f06b4cfa947a259af2548;p=finddup.git diff --git a/finddup.c b/finddup.c index 7a20257..983168b 100644 --- a/finddup.c +++ b/finddup.c @@ -52,7 +52,7 @@ int ignore_dotfiles = 0; /* 1 means ignore files and directories int show_realpaths = 0; /* 1 means ignore files and directories starting with a dot */ -int show_progress = 1; /* 1 means show a progress bar when we are in a +int show_progress = 0; /* 1 means show a progress bar when we are in a tty */ int show_hits = 1; /* 1 means to show the files from dir2 @@ -105,7 +105,7 @@ struct file_with_size { size_t size; ino_t inode; struct file_with_size *next; - int id; + int group_id; }; void file_list_delete(struct file_with_size *head) { @@ -224,7 +224,7 @@ struct file_with_size *scan_directory(struct file_with_size *tail, tmp->filename = strdup(name); tmp->size = sb.st_size; tmp->inode = sb.st_ino; - tmp->id = -1; + tmp->group_id = -1; tail = tmp; } } @@ -233,26 +233,88 @@ struct file_with_size *scan_directory(struct file_with_size *tail, } void print_file(struct file_with_size *node) { + char tmp[PATH_MAX]; if(show_realpaths) { if(show_groups) { - printf("%d %s\n", node->id, realpath(node->filename, 0)); + realpath(node->filename, tmp); + printf("%d %s\n", node->group_id, tmp); } else { - printf("%s\n", realpath(node->filename, 0)); + realpath(node->filename, tmp); + printf("%s\n", tmp); } } else { if(show_groups) { - printf("%d %s\n", node->id, node->filename); + printf("%d %s\n", node->group_id, node->filename); } else { printf("%s\n", node->filename); } } } +int compare_nodes(const void *x1, const void *x2) { + const struct file_with_size **f1, **f2; + + f1 = (const struct file_with_size **) x1; + f2 = (const struct file_with_size **) x2; + + if((*f1)->group_id < (*f2)->group_id) { + return -1; + } else if((*f1)->group_id > (*f2)->group_id) { + return 1; + } else { + return 0; + } +} + + +void print_result(struct file_with_size *list1, struct file_with_size *list2) { + struct file_with_size *node1, *node2; + struct file_with_size **nodes; + int nb, n; + + nb = 0; + for(node1 = list1; node1; node1 = node1->next) { + if(node1->group_id >= 0) { nb++; } + } + + if(show_hits) { + for(node2 = list2; node2; node2 = node2->next) { + if(node2->group_id >= 0) { nb++; } + } + } + + nodes = safe_malloc(nb * sizeof(struct file_with_size *)); + + n = 0; + for(node1 = list1; node1; node1 = node1->next) { + if(node1->group_id >= 0) { + nodes[n++] = node1; + } + } + + if(show_hits) { + for(node2 = list2; node2; node2 = node2->next) { + if(node2->group_id >= 0) { + nodes[n++] = node2; + } + } + } + + qsort(nodes, nb, sizeof(struct file_with_size *), compare_nodes); + + for(n = 0; n < nb; n++) { + print_file(nodes[n]); + } + + free(nodes); +} + void start(const char *dirname1, const char *dirname2) { struct file_with_size *list1, *list2; struct file_with_size *node1, *node2; struct stat sb1, sb2; int not_in, found, same_dir; + int k, p, pp, l1, n; if(strncmp(dirname2, "not:", 4) == 0) { not_in = 1; @@ -273,18 +335,41 @@ void start(const char *dirname1, const char *dirname2) { same_dir = (sb1.st_ino == sb2.st_ino); - fprintf(stderr, "Scanning %s ... ", dirname1); + if(show_progress) { + fprintf(stderr, "Scanning %s ... ", dirname1); + } + list1 = scan_directory(0, dirname1); + if(same_dir) { list2 = list1; } else { - fprintf(stderr, "%s ... ", dirname2); + if(show_progress) { + fprintf(stderr, "%s ... ", dirname2); + } list2 = scan_directory(0, dirname2); } - fprintf(stderr, "done.\n"); + + if(show_progress) { + fprintf(stderr, "done.\n"); + } + + k = 0; + pp = -1; + n = 0; + l1 = file_list_length(list1); if(not_in) { for(node1 = list1; node1; node1 = node1->next) { + if(show_progress) { + p = (100 * n)/l1; + if(p > pp) { + fprintf(stderr, "%d%%\n", p); + pp = p; + } + n++; + } + found = 0; for(node2 = list2; !found && node2; node2 = node2->next) { @@ -303,31 +388,36 @@ void start(const char *dirname1, const char *dirname2) { } } else { - int k = 0; - for(node1 = list1; node1; node1 = node1->next) { + if(show_progress) { + p = (100 * n)/l1; + if(p > pp) { + fprintf(stderr, "%d%%\n", p); + pp = p; + } + n++; + } + for(node2 = list2; node2; node2 = node2->next) { if(node1->inode != node2->inode && same_files(node1, node2)) { - if(node1->id < 0) { - if(node2->id >= 0) { - node1->id = node2->id; + if(node1->group_id < 0) { + if(node2->group_id >= 0) { + node1->group_id = node2->group_id; } else { - node1->id = k; + node1->group_id = k; k++; } - print_file(node1); } - if(node2->id < 0) { - node2->id = node1->id; - if(show_hits) { - print_file(node2); - } + if(node2->group_id < 0) { + node2->group_id = node1->group_id; } } } } } + print_result(list1, list2); + file_list_delete(list1); if(!same_dir) { file_list_delete(list2); @@ -343,6 +433,7 @@ void print_help(FILE *out) { fprintf(out, " -d ignore dot files and directories\n"); fprintf(out, " -c do not show which files in DIR2 corresponds to those in DIR1\n"); fprintf(out, " -g do not show the file groups\n"); + fprintf(out, " -p show progress\n"); fprintf(out, " -r show the real file paths\n"); fprintf(out, "\n"); fprintf(out, "Report bugs and comments to \n"); @@ -359,7 +450,7 @@ int main(int argc, char **argv) { setlocale (LC_ALL, ""); while (1) { - c = getopt(argc, argv, "hrcgd"); + c = getopt(argc, argv, "hrcgdp"); if (c == -1) break; @@ -383,6 +474,10 @@ int main(int argc, char **argv) { show_groups = 0; break; + case 'p': + show_progress = 1; + break; + case 'c': show_hits = 0; break;