New API call iso_write_opts_set_untranslated_name_len()

libisofs/ecma119.c

@@ -141,7 +141,7 @@ static int show_chunk_to_jte(Ecma119Image *target, char *buf, int count)
 static
 int need_version_number(Ecma119Image *t, Ecma119Node *n)
 {
-    if (t->omit_version_numbers & 1) {
+    if ((t->omit_version_numbers & 1) || t->untranslated_name_len > 0) {
         return 0;
     }
     if (n->type == ECMA119_DIR || n->type == ECMA119_PLACEHOLDER) {
@@ -188,9 +188,9 @@ size_t calc_dir_size(Ecma119Image *t, Ecma119Node *dir, size_t *ce)
     /* size of "." and ".." entries */
     len = 34 + 34;
     if (t->rockridge) {
-        len += rrip_calc_len(t, dir, 1, 255 - 34, &ce_len);
+        len += rrip_calc_len(t, dir, 1, 34, &ce_len);
         *ce += ce_len;
-        len += rrip_calc_len(t, dir, 2, 255 - 34, &ce_len);
+        len += rrip_calc_len(t, dir, 2, 34, &ce_len);
         *ce += ce_len;
     }
 
@@ -203,7 +203,7 @@ size_t calc_dir_size(Ecma119Image *t, Ecma119Node *dir, size_t *ce)
         for (section = 0; section < nsections; ++section) {
             size_t dirent_len = calc_dirent_len(t, child);
             if (t->rockridge) {
-                dirent_len += rrip_calc_len(t, child, 0, 255 - dirent_len, &ce_len);
+                dirent_len += rrip_calc_len(t, child, 0, dirent_len, &ce_len);
                 *ce += ce_len;
             }
             remaining = BLOCK_SIZE - (len % BLOCK_SIZE);
@@ -594,7 +594,7 @@ int write_one_dir(Ecma119Image *t, Ecma119Node *dir, Ecma119Node *parent)
 
     /* write the "." and ".." entries first */
     if (t->rockridge) {
-        ret = rrip_get_susp_fields(t, dir, 1, 255 - 32, &info);
+        ret = rrip_get_susp_fields(t, dir, 1, 34, &info);
         if (ret < 0) {
             return ret;
         }
@@ -604,7 +604,7 @@ int write_one_dir(Ecma119Image *t, Ecma119Node *dir, Ecma119Node *parent)
     buf += len;
 
     if (t->rockridge) {
-        ret = rrip_get_susp_fields(t, dir, 2, 255 - 32, &info);
+        ret = rrip_get_susp_fields(t, dir, 2, 34, &info);
         if (ret < 0) {
             return ret;
         }
@@ -630,7 +630,7 @@ int write_one_dir(Ecma119Image *t, Ecma119Node *dir, Ecma119Node *parent)
 
             /* get the SUSP fields if rockridge is enabled */
             if (t->rockridge) {
-                ret = rrip_get_susp_fields(t, child, 0, 255 - len, &info);
+                ret = rrip_get_susp_fields(t, child, 0, len, &info);
                 if (ret < 0) {
                     return ret;
                 }
@@ -1575,6 +1575,7 @@ int ecma119_image_new(IsoImage *src, IsoWriteOpts *opts, Ecma119Image **img)
     target->hardlinks = opts->hardlinks;
     target->aaip = opts->aaip;
     target->always_gmt = opts->always_gmt;
+    target->untranslated_name_len = opts->untranslated_name_len;
     target->omit_version_numbers = opts->omit_version_numbers
                                  | opts->max_37_char_filenames;
     target->allow_deep_paths = opts->allow_deep_paths;
@@ -2363,6 +2364,7 @@ int iso_write_opts_new(IsoWriteOpts **opts, int profile)
         wopts->appended_partitions[i] = NULL;
     wopts->ascii_disc_label[0] = 0;
     wopts->will_cancel = 0;
+    wopts->untranslated_name_len = 0;
 
     *opts = wopts;
     return ISO_SUCCESS;
@@ -2451,6 +2453,22 @@ int iso_write_opts_set_aaip(IsoWriteOpts *opts, int enable)
     return ISO_SUCCESS;
 }
 
+int iso_write_opts_set_untranslated_name_len(IsoWriteOpts *opts, int len)
+{
+    if (opts == NULL) {
+        return ISO_NULL_POINTER;
+    }
+    if (len == -1)
+        opts->untranslated_name_len = ISO_UNTRANSLATED_NAMES_MAX;
+    else if(len == 0)
+        opts->untranslated_name_len = 0;
+    else if(len > ISO_UNTRANSLATED_NAMES_MAX || len < 0)
+        return ISO_WRONG_ARG_VALUE;
+    else
+        opts->untranslated_name_len = len;
+    return opts->untranslated_name_len;
+}
+
 int iso_write_opts_set_omit_version_numbers(IsoWriteOpts *opts, int omit)
 {
     if (opts == NULL) {

libisofs/ecma119.h

@@ -52,6 +52,17 @@
 #define ISO_DISC_LABEL_SIZE 129
 
 
+/* The maximum lenght of an specs violating ECMA-119 file identifier.
+   The theoretical limit is  254 - 34 - 28 (len of SUSP CE entry) = 192
+   Currently the practical limit is 254 - 34 - 96 (non-CE RR entries) - 28 (CE)
+*/
+#ifdef Libisofs_with_rrip_rR
+#define ISO_UNTRANSLATED_NAMES_MAX 92
+#else
+#define ISO_UNTRANSLATED_NAMES_MAX 96
+#endif
+
+
 /**
  * Holds the options for the image generation.
  */
@@ -213,6 +224,21 @@ struct iso_write_opts {
     unsigned int replace_uid :2;
     unsigned int replace_gid :2;
 
+    /**
+     * Extra Caution: This option breaks any assumptions about names that
+     *                are supported by ECMA-119 specifications. 
+     * Omit any translation which would make a file name compliant to the
+     * ECMA-119 rules. This includes and exceeds omit_version_numbers,
+     * max_37_char_filenames, no_force_dots bit0, allow_lowercase.
+     * The maximum name length is given by this variable.
+     * There is a length limit of ISO_UNTRANSLATED_NAMES_MAX characters,
+     * because ECMA-119 allows 254 byte in a directory record, some
+     * of them are occupied by ECMA-119, some more are needed for SUSP CE,
+     * and some are fixely occupied by libisofs Rock Ridge code.
+     * The default value 0 disables this feature.
+     */
+    unsigned int untranslated_name_len;
+
     mode_t dir_mode; /** Mode to use on dirs when replace_dir_mode == 2. */
     mode_t file_mode; /** Mode to use on files when replace_file_mode == 2. */
     uid_t uid; /** uid to use when replace_uid == 2. */
@@ -437,6 +463,8 @@ struct ecma119_image
     unsigned int replace_dir_mode :1;
     unsigned int replace_timestamps :1;
 
+    unsigned int untranslated_name_len;
+
     uid_t uid;
     gid_t gid;
     mode_t file_mode;

libisofs/ecma119_tree.c

@@ -12,6 +12,9 @@
 #include "../config.h"
 #endif
 
+/* Must be before ecma119.h because of eventual Libisofs_with_rrip_rR */
+#include "libisofs.h"
+
 #include "ecma119_tree.h"
 #include "ecma119.h"
 #include "node.h"
@@ -29,7 +32,7 @@
 static
 int get_iso_name(Ecma119Image *img, IsoNode *iso, char **name)
 {
-    int ret, relaxed;
+    int ret, relaxed, free_ascii_name= 0;
     char *ascii_name;
     char *isoname= NULL;
 
@@ -38,9 +41,15 @@ int get_iso_name(Ecma119Image *img, IsoNode *iso, char **name)
         return ISO_SUCCESS;
     }
 
+    if (img->untranslated_name_len > 0) {
+        ascii_name = iso->name;
+    } else {
         ret = str2ascii(img->input_charset, iso->name, &ascii_name);
+        free_ascii_name = 1;
+    }
     if (ret < 0) {
-        iso_msg_submit(img->image->id, ret, 0, "Can't convert %s", iso->name);
+        iso_msg_submit(img->image->id, ret, 0,
+                       "Cannot convert name '%s' to ASCII", iso->name);
         return ret;
     }
 
@@ -50,7 +59,17 @@ int get_iso_name(Ecma119Image *img, IsoNode *iso, char **name)
         relaxed = (int)img->allow_lowercase;
     }
     if (iso->type == LIBISO_DIR) {
-        if (img->max_37_char_filenames) {
+        if (img->untranslated_name_len > 0) {
+            if (strlen(ascii_name) > img->untranslated_name_len) {
+needs_transl:;
+                iso_msg_submit(img->image->id, ISO_NAME_NEEDS_TRANSL, 0,
+              "File name too long (%d > %d) for untranslated recording:  '%s'",
+                               strlen(ascii_name), img->untranslated_name_len,
+                               ascii_name);
+                return ISO_NAME_NEEDS_TRANSL;
+            }
+            isoname = strdup(ascii_name);
+        } else if (img->max_37_char_filenames) {
             isoname = iso_r_dirid(ascii_name, 37, relaxed);
         } else if (img->iso_level == 1) {
             if (relaxed) {
@@ -66,7 +85,11 @@ int get_iso_name(Ecma119Image *img, IsoNode *iso, char **name)
             }
         }
     } else {
-        if (img->max_37_char_filenames) {
+        if (img->untranslated_name_len > 0) {
+            if (strlen(ascii_name) > img->untranslated_name_len)
+                goto needs_transl;
+            isoname = strdup(ascii_name);
+        } else if (img->max_37_char_filenames) {
             isoname = iso_r_fileid(ascii_name, 36, relaxed,
                                    (img->no_force_dots & 1) ? 0 : 1);
         } else if (img->iso_level == 1) {
@@ -85,6 +108,7 @@ int get_iso_name(Ecma119Image *img, IsoNode *iso, char **name)
             }
         }
     }
+    if (free_ascii_name)
         free(ascii_name);
     if (isoname != NULL) {
         *name = isoname;
@@ -416,8 +440,6 @@ int create_tree(Ecma119Image *image, IsoNode *iso, Ecma119Node **tree,
                                    !!hidden);
                 if (cret < 0) {
                     /* error */
-                    if (!hidden)
-                        ecma119_node_free(node);
                     ret = cret;
                     break;
                 } else if (cret == ISO_SUCCESS && !hidden) {
@@ -537,6 +559,18 @@ int mangle_single_dir(Ecma119Image *img, Ecma119Node *dir, int max_file_len,
             continue;
         }
 
+        if (img->untranslated_name_len) {
+            /* This should not happen because no two IsoNode names should be
+               identical and only unaltered IsoNode names should be seen here.
+               Thus the Ema119Node names should be unique.
+            */
+            iso_msg_submit(img->image->id, ISO_NAME_NEEDS_TRANSL, 0,
+                           "ECMA-119 file name collision: '%s'",
+                           children[i]->iso_name);
+            ret = ISO_NAME_NEEDS_TRANSL;
+            goto mangle_cleanup;
+        }
+
         /*
          * A max of 7 characters is good enought, it allows handling up to
          * 9,999,999 files with same name. We can increment this to
@@ -716,7 +750,9 @@ int mangle_tree(Ecma119Image *img, int recurse)
     int max_file, max_dir;
     Ecma119Node *root;
 
-    if (img->max_37_char_filenames) {
+    if (img->untranslated_name_len > 0) {
+        max_file = max_dir = img->untranslated_name_len;
+    } else if (img->max_37_char_filenames) {
         max_file = max_dir = 37;
     } else if (img->iso_level == 1) {
         max_file = 12; /* 8 + 3 + 1 */

libisofs/libisofs.h

@@ -1344,6 +1344,34 @@ int iso_write_opts_set_hardlinks(IsoWriteOpts *opts, int enable);
  */
 int iso_write_opts_set_aaip(IsoWriteOpts *opts, int enable);
 
+/**
+ * Caution: This option breaks any assumptions about names that
+ *          are supported by ECMA-119 specifications. 
+ * Try to omit any translation which would make a file name compliant to the
+ * ECMA-119 rules. This includes and exceeds omit_version_numbers,
+ * max_37_char_filenames, no_force_dots bit0, allow_full_ascii. Further it
+ * prevents the conversion from local character set to ASCII.
+ * The maximum name length is given by this call. If a filename exceeds
+ * this length or cannot be recorded untranslated for other reasons, then
+ * image production is aborted with ISO_NAME_NEEDS_TRANSL.
+ * Currently the length limit is 96 characters, because an ECMA-119 directory
+ * record may at most have 254 bytes and up to 158 other bytes must fit into
+ * the record. Probably 96 more bytes can be made free for the name in future.
+ * @param opts
+ *      The option set to be manipulated.
+ * @param len
+ *      0 = disable this feature and perform name translation according to
+ *          other settings.
+ *     >0 = Omit any translation. Eventually abort image production
+ *          if a name is longer than the given value.
+ *     -1 = Like >0. Allow maximum possible length (currently 96)
+ * @return >=0 success, <0 failure
+ *         In case of >=0 the return value tells the effectively set len.
+ *         E.g. 96 after using len == -1.
+ * @since 0.6.42
+ */
+int iso_write_opts_set_untranslated_name_len(IsoWriteOpts *opts, int len);
+
 /**
  * Omit the version number (";1") at the end of the ISO-9660 identifiers.
  * This breaks ECMA-119 specification, but version numbers are usually not
@@ -6422,6 +6450,9 @@ int iso_md5_match(char first_md5[16], char second_md5[16]);
 /** Displacement offset leads outside 32 bit range (FAILURE, HIGH, -372) */
 #define ISO_DISPLACE_ROLLOVER      0xE830FE8C
 
+/** File name cannot be written into ECMA-119 untranslated
+                                                       (FAILURE, HIGH, -373) */
+#define ISO_NAME_NEEDS_TRANSL      0xE830FE8B
 
 
 /* Internal developer note: 

libisofs/libisofs.ver

@@ -293,6 +293,7 @@ iso_write_opts_set_scdbackup_tag;
 iso_write_opts_set_sort_files;
 iso_write_opts_set_system_area;
 iso_write_opts_set_tail_blocks;
+iso_write_opts_set_untranslated_name_len;
 iso_write_opts_set_will_cancel;
 iso_zisofs_get_params;
 iso_zisofs_get_refcounts;

libisofs/messages.c

@@ -361,6 +361,8 @@ const char *iso_error_to_msg(int errcode)
         return "May not combine appended partition with non-MBR system area";
     case ISO_DISPLACE_ROLLOVER:
         return "Displacement offset leads outside 32 bit range";
+    case ISO_NAME_NEEDS_TRANSL:
+        return "File name cannot be written into ECMA-119 untranslated";
     default:
         return "Unknown error";
     }

libisofs/rockridge.c

@@ -13,6 +13,9 @@
 #include "../config.h"
 #endif
 
+#include <string.h>
+#include <stdio.h>
+
 #include "rockridge.h"
 #include "node.h"
 #include "ecma119_tree.h"
@@ -22,7 +25,12 @@
 #include "aaip_0_2.h"
 #include "libisofs.h"
 
-#include <string.h>
+
+#ifdef Libisofs_with_rrip_rR
+#define ISO_ROCKRIDGE_IN_DIR_REC 128
+#else
+#define ISO_ROCKRIDGE_IN_DIR_REC 124
+#endif
 
 
 static
@@ -1104,27 +1112,30 @@ unannounced_ca:;
  * @param type
  *      0 normal entry, 1 "." entry for that node (it is a dir), 2 ".."
  *      for that node (i.e., it will refer to the parent)
- * @param space
+ * @param used_up
- *      Available space in the System Use Area for the directory record.
+ *      Already occupied space in the directory record.
  * @param ce
  *      Will be filled with the space needed in a CE
  * @return
  *      The size needed for the RR entries in the System Use Area
  */
-size_t rrip_calc_len(Ecma119Image *t, Ecma119Node *n, int type, size_t space,
+size_t rrip_calc_len(Ecma119Image *t, Ecma119Node *n, int type, size_t used_up,
                      size_t *ce)
 {
-    size_t su_size;
+    size_t su_size, space;
     int ret;
 
-    /* space min is 255 - 33 - 37 = 185
+    /* Directory record length must be even (ECMA-119, 9.1.13). Maximum is 254.
-     * At the same time, it is always an odd number, but we need to pad it
-     * propertly to ensure the length of a directory record is a even number
-     * (ECMA-119, 9.1.13). Thus, in fact the real space is always space - 1
     */
-    space--;
+    space = 254 - used_up - (used_up % 2);
-    *ce = 0;
+    if (type < 0 || type > 2 || space < ISO_ROCKRIDGE_IN_DIR_REC) {
+        iso_msg_submit(t->image->id, ISO_ASSERT_FAILURE, 0,
+          "Unknown node type %d or short RR space %d < %d in directory record",
+          type, (int) space, ISO_ROCKRIDGE_IN_DIR_REC);
+        return ISO_ASSERT_FAILURE;
+    }
 
+    *ce = 0;
     su_size = 0;
 
     /* If AAIP enabled and announced by ER : account for 5 bytes of ES */;
@@ -1268,8 +1279,8 @@ int add_aa_string(Ecma119Image *t, Ecma119Node *n, struct susp_info *info,
  * @param type
  *      0 normal entry, 1 "." entry for that node (it is a dir), 2 ".."
  *      for that node (i.e., it will refer to the parent)
- * @param space
+ * @param used_up
- *      Available space in the System Use Area for the directory record.
+ *      Already occupied space in the directory record.
  * @param info
  *      Pointer to the struct susp_info where the entries will be stored.
  *      If some entries need to go to a Continuation Area, they will be added
@@ -1279,7 +1290,7 @@ int add_aa_string(Ecma119Image *t, Ecma119Node *n, struct susp_info *info,
  *      1 success, < 0 error
  */
 int rrip_get_susp_fields(Ecma119Image *t, Ecma119Node *n, int type,
-                         size_t space, struct susp_info *info)
+                         size_t used_up, struct susp_info *info)
 {
     int ret;
     size_t i;
@@ -1291,13 +1302,20 @@ int rrip_get_susp_fields(Ecma119Image *t, Ecma119Node *n, int type,
     size_t su_size_pd, ce_len_pd; /* predicted sizes of SUA and CA */
     int ce_is_predicted = 0;
     size_t aaip_sua_free= 0, aaip_len= 0;
+    size_t space;
 
     if (t == NULL || n == NULL || info == NULL) {
         return ISO_NULL_POINTER;
     }
-    if (type < 0 || type > 2 || space < 185) {
+
-        /* space min is 255 - 33 - 37 = 185 */
+    /* Directory record length must be even (ECMA-119, 9.1.13). Maximum is 254.
-        return ISO_WRONG_ARG_VALUE;
+    */
+    space = 254 - used_up - (used_up % 2);
+    if (type < 0 || type > 2 || space < ISO_ROCKRIDGE_IN_DIR_REC) {
+        iso_msg_submit(t->image->id, ISO_ASSERT_FAILURE, 0,
+          "Unknown node type %d or short RR space %d < %d in directory record",
+          type, (int) space, ISO_ROCKRIDGE_IN_DIR_REC);
+        return ISO_ASSERT_FAILURE;
     }
 
     if (type == 2 && n->parent != NULL) {
@@ -1306,13 +1324,6 @@ int rrip_get_susp_fields(Ecma119Image *t, Ecma119Node *n, int type,
         node = n;
     }
 
-    /* space min is 255 - 33 - 37 = 185
-     * At the same time, it is always an odd number, but we need to pad it
-     * propertly to ensure the length of a directory record is a even number
-     * (ECMA-119, 9.1.13). Thus, in fact the real space is always space - 1
-     */
-    space--;
-
     /* 
      * SP must be the first entry for the "." record of the root directory
      * (SUSP, 5.3)
@@ -1384,6 +1395,16 @@ int rrip_get_susp_fields(Ecma119Image *t, Ecma119Node *n, int type,
         }
     }
 
+
+    /* <<< ts B01222 : For testing only */
+    if (info->suf_len + 28 > space) {
+        fprintf(stderr,
+                "libisofs_debug: Directory Record overflow. name='%s' , info->suf_len=%d > space=%d - 28\n", 
+                node->iso_name, (int) info->suf_len, (int) space);
+        return ISO_ASSERT_FAILURE;
+    }
+
+
     if (type == 0) {
         size_t sua_free; /* free space in the SUA */
         int nm_type = 0; /* 0 whole entry in SUA, 1 part in CE */

libisofs/util.c

@@ -773,6 +773,8 @@ char *iso_r_dirid(const char *src, int size, int relaxed)
         len = size;
     }
     dest = malloc(len + 1);
+    if (dest == NULL)
+        return NULL;
     for (i = 0; i < len; i++) {
         char c= src[i];
         if (relaxed == 2) {
@@ -1036,6 +1038,8 @@ uint16_t *ucsdup(const uint16_t *str)
     size_t len = ucslen(str);
     
     ret = malloc(2 * (len + 1));
+    if (ret == NULL)
+        return NULL;
     if (ret != NULL) {
         memcpy(ret, str, 2 * (len + 1));
     }
@@ -1460,6 +1464,8 @@ char *ucs2str(const char *buf, size_t len)
     
     /* ensure enought space */
     out = calloc(outbytes, 1);
+    if (out == NULL)
+        return NULL;
 
     /* convert to local charset */
     conv_ret = iso_iconv_open(&conv, iso_get_local_charset(0), "UCS-2BE", 0);