#! /bin/sh /usr/share/dpatch/dpatch-run ## 50_bts284274_hardlinkreplace.dpatch by ## ## All lines beginning with `## DP:' are a description of the patch. ## DP: Replace duplicate files with hardlinks @DPATCH@ Index: fdupes-1.6.1/fdupes.c =================================================================== --- fdupes-1.6.1.orig/fdupes.c 2016-11-04 14:37:27.771346294 +0100 +++ fdupes-1.6.1/fdupes.c 2016-11-04 14:44:50.631242166 +0100 @@ -54,6 +54,8 @@ #define F_PERMISSIONS 0x2000 #define F_REVERSE 0x4000 #define F_IMMEDIATE 0x8000 +#define F_HARDLINKFILES 0x10000 +#define F_DEBUGINFO 0x20000 typedef enum { ORDER_TIME = 0, @@ -903,6 +905,88 @@ void deletefiles(file_t *files, int prom free(preservestr); } +void hardlinkfiles(file_t *files, int debug) +{ + int counter; + int groups = 0; + int curgroup = 0; + file_t *tmpfile; + file_t *curfile; + file_t **dupelist; + int max = 0; + int x = 0; + + curfile = files; + + while (curfile) { + if (curfile->hasdupes) { + counter = 1; + groups++; + + tmpfile = curfile->duplicates; + while (tmpfile) { + counter++; + tmpfile = tmpfile->duplicates; + } + + if (counter > max) max = counter; + } + + curfile = curfile->next; + } + + max++; + + dupelist = (file_t**) malloc(sizeof(file_t*) * max); + + if (!dupelist) { + errormsg("out of memory\n"); + exit(1); + } + + while (files) { + if (files->hasdupes) { + curgroup++; + counter = 1; + dupelist[counter] = files; + + if (debug) printf("[%d] %s\n", counter, files->d_name); + + tmpfile = files->duplicates; + + while (tmpfile) { + dupelist[++counter] = tmpfile; + if (debug) printf("[%d] %s\n", counter, tmpfile->d_name); + tmpfile = tmpfile->duplicates; + } + + if (debug) printf("\n"); + + /* preserve only the first file */ + + printf(" [+] %s\n", dupelist[1]->d_name); + for (x = 2; x <= counter; x++) { + if (unlink(dupelist[x]->d_name) == 0) { + if ( link(dupelist[1]->d_name, dupelist[x]->d_name) == 0 ) { + printf(" [h] %s\n", dupelist[x]->d_name); + } else { + printf("-- unable to create a hardlink for the file: %s\n", strerror(errno)); + printf(" [!] %s ", dupelist[x]->d_name); + } + } else { + printf(" [!] %s ", dupelist[x]->d_name); + printf("-- unable to delete the file!\n"); + } + } + printf("\n"); + } + + files = files->next; + } + + free(dupelist); +} + int sort_pairs_by_arrival(file_t *f1, file_t *f2) { if (f2->duplicates != 0) @@ -1030,12 +1114,14 @@ void help_text() printf(" \twith -s or --symlinks, or when specifying a\n"); printf(" \tparticular directory more than once; refer to the\n"); printf(" \tfdupes documentation for additional information\n"); - /*printf(" -l --relink \t(description)\n");*/ + printf(" -L --linkhard \thardlink duplicate files to the first file in\n"); + printf(" \teach set of duplicates without prompting the user\n"); printf(" -N --noprompt \ttogether with --delete, preserve the first file in\n"); printf(" \teach set of duplicates and delete the rest without\n"); printf(" \tprompting the user\n"); printf(" -I --immediate \tdelete duplicates as they are encountered, without\n"); printf(" \tgrouping into sets; implies --noprompt\n"); + printf(" -D --debug \tenable debugging information\n"); printf(" -p --permissions \tdon't consider files with different owner/group or\n"); printf(" \tpermission bits as duplicates\n"); printf(" -o --order=BY \tselect sort order for output, linking and deleting; by\n"); @@ -1077,6 +1163,7 @@ int main(int argc, char **argv) { { "symlinks", 0, 0, 's' }, { "hardlinks", 0, 0, 'H' }, { "relink", 0, 0, 'l' }, + { "linkhard", 0, 0, 'L' }, { "noempty", 0, 0, 'n' }, { "nohidden", 0, 0, 'A' }, { "delete", 0, 0, 'd' }, @@ -1084,6 +1171,7 @@ int main(int argc, char **argv) { { "help", 0, 0, 'h' }, { "noprompt", 0, 0, 'N' }, { "immediate", 0, 0, 'I'}, + { "debug", 0, 0, 'D' }, { "summarize", 0, 0, 'm'}, { "summary", 0, 0, 'm' }, { "permissions", 0, 0, 'p' }, @@ -1100,7 +1188,7 @@ int main(int argc, char **argv) { oldargv = cloneargs(argc, argv); - while ((opt = GETOPT(argc, argv, "frRq1SsHlnAdvhNImpo:i" + while ((opt = GETOPT(argc, argv, "frRq1SsHlLnAdDvhNImpo:i" #ifndef OMIT_GETOPT_LONG , long_options, NULL #endif @@ -1139,6 +1227,12 @@ int main(int argc, char **argv) { case 'd': SETFLAG(flags, F_DELETEFILES); break; + case 'L': + SETFLAG(flags, F_HARDLINKFILES); + break; + case 'D': + SETFLAG(flags, F_DEBUGINFO); + break; case 'v': printf("fdupes %s\n", VERSION); exit(0); @@ -1192,6 +1286,16 @@ int main(int argc, char **argv) { exit(1); } + if (ISFLAG(flags, F_HARDLINKFILES) && ISFLAG(flags, F_DELETEFILES)) { + errormsg("options --linkhard and --delete are not compatible\n"); + exit(1); + } + + if (ISFLAG(flags, F_HARDLINKFILES) && ISFLAG(flags, F_CONSIDERHARDLINKS)) { + errormsg("options --linkhard and --hardlinks are not compatible\n"); + exit(1); + } + if (ISFLAG(flags, F_RECURSEAFTER)) { firstrecurse = nonoptafter("--recurse:", argc, oldargv, argv, optind); @@ -1288,6 +1392,15 @@ int main(int argc, char **argv) { else + if (ISFLAG(flags, F_HARDLINKFILES)) + + if (ISFLAG(flags, F_DEBUGINFO)) + hardlinkfiles(files, 1); + else + hardlinkfiles(files, 0); + + else { + if (ISFLAG(flags, F_SUMMARIZEMATCHES)) summarizematches(files); @@ -1295,6 +1408,8 @@ int main(int argc, char **argv) { printmatches(files); + } + while (files) { curfile = files->next; free(files->d_name); Index: fdupes-1.6.1/fdupes.1 =================================================================== --- fdupes-1.6.1.orig/fdupes.1 2016-11-04 14:37:31.507413478 +0100 +++ fdupes-1.6.1/fdupes.1 2016-11-04 14:38:38.500615178 +0100 @@ -59,6 +59,10 @@ prompt user for files to preserve, delet .B CAVEATS below) .TP +.B -L --hardlink +replace all duplicate files with hardlinks to the +first file in each set of duplicates +.TP .B -N --noprompt when used together with \-\-delete, preserve the first file in each set of duplicates and delete the others without prompting the user @@ -67,6 +71,9 @@ set of duplicates and delete the others delete duplicates as they are encountered, without grouping into sets; implies --noprompt .TP +.B -D --debug +provide debugging information +.TP .B -p --permissions don't consider files with different owner/group or permission bits as duplicates .TP