uid and paths separator "~" in place of ":"

need a character to split filenames on in certain circumstances.
there problems with use of a colon in filenames, which is legal on posix
but not on Windows."~" fits the bill better being legal on every
filesystem of interest and is unreserved in rfc 3986, needing no escaping in a url.

The reference abstraction is renamed, its content unchanged. Over
the sample collection two filenames move and nothing else does: the
abstraction and database digests are identical, the archive's
members and their sizes are unchanged, and only the member order
shifts, "~" collating after letters where ":" sorted before them. The
document's epub dc:identifier is a v5 uuid derived from the uid, so it
changes for those filenames.

Every document's uid changes in the search database (spine.search.db).

(assisted by Claude-Code)

7 files changed, 44 insertions, 37 deletions

diff --git a/src/sisudoc/ocda/io_in/carried_names.d b/src/sisudoc/ocda/io_in/carried_names.d
index 84a4f3c..eaa233d 100644
--- a/src/sisudoc/ocda/io_in/carried_names.d
+++ b/src/sisudoc/ocda/io_in/carried_names.d
@@ -128,9 +128,14 @@ template spineCarriedNames() {
   enum size_t MAX_CARRIED_NAME_LENGTH = 255;               /+ one path component +/
   enum size_t MAX_CARRIED_PATH_LENGTH = 1024;              /+ the whole path +/
   enum size_t MAX_CARRIED_PATH_DEPTH  = 10;                /+ as read_zip_pod.d +/
-  /+ ↓ allowed characters: a filename has no separator, a path has "/" +/
-  static auto rgx_safe_carried_name = ctRegex!(`^[a-zA-Z0-9._ -]+$`);
-  static auto rgx_safe_carried_path = ctRegex!(`^[a-zA-Z0-9._/ -]+$`);
+  /+ ↓ allowed characters: a filename has no separator, a path has "/".
+       "~" is here because it is spine's own uid separator (InlineMarkup.uid_sep),
+       which joins a pod name to a document name where the two differ, as in
+       sisu-manual~sisu_markup.en.ssp. It cannot occur in either half, every
+       filesystem of interest takes it, and it is unreserved in rfc 3986.
+  +/
+  static auto rgx_safe_carried_name = ctRegex!(`^[a-zA-Z0-9._ ~-]+$`);
+  static auto rgx_safe_carried_path = ctRegex!(`^[a-zA-Z0-9._/ ~-]+$`);
   /+ ↓ the checks both rules share, "" when the name is acceptable +/
   private string _carriedNameCommon(string _name) {
     if (_name.length == 0) {
diff --git a/src/sisudoc/ocda/io_in/read_zip_pod.d b/src/sisudoc/ocda/io_in/read_zip_pod.d
index 18a957c..c96429b 100644
--- a/src/sisudoc/ocda/io_in/read_zip_pod.d
+++ b/src/sisudoc/ocda/io_in/read_zip_pod.d
@@ -75,8 +75,10 @@ template spineExtractZipPod() {
   alias MAX_ENTRY_COUNT = MAX_POD_ENTRY_COUNT;
   enum size_t MAX_PATH_DEPTH     = 10;                  /+ max path components +/
 
-  /+ allowed entry name pattern: alphanumeric, dots, dashes, underscores, forward slashes +/
-  static auto rgx_safe_entry_name = ctRegex!(`^[a-zA-Z0-9._/ -]+$`);
+  /+ allowed entry name pattern: alphanumeric, dots, dashes, underscores,
+     forward slashes, and "~", spine's own uid separator (as carried_names.d)
+  +/
+  static auto rgx_safe_entry_name = ctRegex!(`^[a-zA-Z0-9._/ ~-]+$`);
 
   struct ZipPodResult {
     string tmp_dir;          /+ temp directory containing extracted pod +/
diff --git a/src/sisudoc/ocda/meta/defaults.d b/src/sisudoc/ocda/meta/defaults.d
index 91df996..59dcc87 100644
--- a/src/sisudoc/ocda/meta/defaults.d
+++ b/src/sisudoc/ocda/meta/defaults.d
@@ -196,7 +196,7 @@ template InternalMarkup() {
     string tc_p                   = "┆";
     string img                    = "☼";
     string sep                    = "␣"; // "~";"␣"; // "~";
-    string uid_sep                = ":";
+    string uid_sep                = "~";
     string on_o  = "「";       string on_c  = "」";
     string mk_bullet               = "● ";
     static string indent_by_spaces_provided(int indent, string _indent_spaces ="░░") {
diff --git a/src/sisudoc/ocda/meta/rgx.d b/src/sisudoc/ocda/meta/rgx.d
index d3c9aa1..125fb52 100644
--- a/src/sisudoc/ocda/meta/rgx.d
+++ b/src/sisudoc/ocda/meta/rgx.d
@@ -208,17 +208,17 @@ static template spineRgxIn() {
     static nbsp_char                                = ctRegex!(`░`, "mg");
     static nbsp_chars                               = ctRegex!(`[░]+`, "mg");
     static middle_dot                               = ctRegex!(`·`, "mg");
-    static src_pth_sst_or_ssm                       = ctRegex!(`^(?P<path>[/]?(?:[a-zA-Z0-9._-]+/)*)(?P<filename>[a-zA-Z0-9._-]+[.](?P<extension>ss[tm]))$`);
-    static src_pth_pod_sst_or_ssm                   = ctRegex!(`^(?P<podpath>[/]?(?:[a-zA-Z0-9._-]+/)*)media/text/[a-z]{2}/(?P<filename>[a-zA-Z0-9][a-zA-Z0-9._-]*?[.]ss[tm])$`);
-    static src_pth_contents                         = ctRegex!(`^(?P<path>[/]?(?:[a-zA-Z0-9._-]+/)*)(?P<filename>[a-zA-Z0-9][a-zA-Z0-9._-]*)/pod[.]manifest$`);
-    static src_pth_zip                              = ctRegex!(`^(?P<path>[/]?(?:[a-zA-Z0-9._-]+/)*)(?P<filename>[a-zA-Z0-9._-]+(?:[.]zip|[.]sisupod))$`);
-    static src_pth_types                            = ctRegex!(`^(?P<path>[/]?[a-zA-Z0-9._-]+/)*(?P<gotfile>(?P<filename>[a-zA-Z0-9._-]+[.]ss[tm])|(?P<filelist>[a-zA-Z0-9._-]+/pod[.]manifest)|(?P<filezip>[a-zA-Z0-9._-]+(?:[.]zip|[.]sisupod)))$`);
-    static src_fn                                   = ctRegex!(`^([/]?(?:[a-zA-Z0-9._-]+/)*)(?P<fn_src>(?P<fn_base>[a-zA-Z0-9._-]+)[.](?P<fn_src_suffix>ss[tm]))$`);
-    static src_fn_master                            = ctRegex!(`^(?P<path>/?(?:[a-zA-Z0-9._-]+/)*)(?P<filename>[a-zA-Z0-9._-]+[.]ssm)$`);
-    static src_fn_find_inserts                      = ctRegex!(`^(?P<path>/?(?:[a-zA-Z0-9._-]+/)*)(?P<filename>[a-zA-Z0-9._-]+[.]ss[im])$`);
+    static src_pth_sst_or_ssm                       = ctRegex!(`^(?P<path>[/]?(?:[a-zA-Z0-9._:~-]+/)*)(?P<filename>[a-zA-Z0-9._-]+[.](?P<extension>ss[tm]))$`);
+    static src_pth_pod_sst_or_ssm                   = ctRegex!(`^(?P<podpath>[/]?(?:[a-zA-Z0-9._:~-]+/)*)media/text/[a-z]{2}/(?P<filename>[a-zA-Z0-9][a-zA-Z0-9._-]*?[.]ss[tm])$`);
+    static src_pth_contents                         = ctRegex!(`^(?P<path>[/]?(?:[a-zA-Z0-9._:~-]+/)*)(?P<filename>[a-zA-Z0-9][a-zA-Z0-9._-]*)/pod[.]manifest$`);
+    static src_pth_zip                              = ctRegex!(`^(?P<path>[/]?(?:[a-zA-Z0-9._:~-]+/)*)(?P<filename>[a-zA-Z0-9._-]+(?:[.]zip|[.]sisupod))$`);
+    static src_pth_types                            = ctRegex!(`^(?P<path>[/]?[a-zA-Z0-9._:~-]+/)*(?P<gotfile>(?P<filename>[a-zA-Z0-9._-]+[.]ss[tm])|(?P<filelist>[a-zA-Z0-9._-]+/pod[.]manifest)|(?P<filezip>[a-zA-Z0-9._-]+(?:[.]zip|[.]sisupod)))$`);
+    static src_fn                                   = ctRegex!(`^([/]?(?:[a-zA-Z0-9._:~-]+/)*)(?P<fn_src>(?P<fn_base>[a-zA-Z0-9._-]+)[.](?P<fn_src_suffix>ss[tm]))$`);
+    static src_fn_master                            = ctRegex!(`^(?P<path>/?(?:[a-zA-Z0-9._:~-]+/)*)(?P<filename>[a-zA-Z0-9._-]+[.]ssm)$`);
+    static src_fn_find_inserts                      = ctRegex!(`^(?P<path>/?(?:[a-zA-Z0-9._:~-]+/)*)(?P<filename>[a-zA-Z0-9._-]+[.]ss[im])$`);
     static insert_src_fn_ssi_or_sst                 = ctRegex!(`^<<\s*(?P<path>[a-zA-Z0-9._-]+/)*(?P<filename>[a-zA-Z0-9._-]+[.]ss[ti])$`);
-    static src_base_parent_dir_name                 = ctRegex!(`[/](?P<dir>(?:[a-zA-Z0-9._-]+))(?:/media/text/[a-z]{2})$`); // formalizes dir structure
-    static src_formalised_file_path_parts           = ctRegex!(`(?P<pth>(?:[/a-zA-Z0-9._-]+?)(?P<dir>[a-zA-Z0-9._-]+))(?:/media/text/[a-z]{2})$`); // formalizes dir structure
+    static src_base_parent_dir_name                 = ctRegex!(`[/](?P<dir>(?:[a-zA-Z0-9._:~-]+))(?:/media/text/[a-z]{2})$`); // formalizes dir structure
+    static src_formalised_file_path_parts           = ctRegex!(`(?P<pth>(?:[/a-zA-Z0-9._:~-]+?)(?P<dir>[a-zA-Z0-9._:~-]+))(?:/media/text/[a-z]{2})$`); // formalizes dir structure
     /+ line breaks +/
     static br_empty_line                            = ctRegex!(`\n[ ]*\n`, "mg");
     static br_linebreaks_newlines                   = ctRegex!(`[\n┘┙]`, "mg");
diff --git a/src/sisudoc/ocda/meta/rgx_files.d b/src/sisudoc/ocda/meta/rgx_files.d
index 13c7e46..a20eca1 100644
--- a/src/sisudoc/ocda/meta/rgx_files.d
+++ b/src/sisudoc/ocda/meta/rgx_files.d
@@ -54,17 +54,17 @@ module sisudoc.ocda.meta.rgx_files;
 @safe:
 static template spineRgxFiles() {
   static struct RgxFiles {
-    static src_pth_sst_or_ssm                       = ctRegex!(`^(?P<path>[/]?(?:[a-zA-Z0-9._-]+/)*)(?P<filename>[a-zA-Z0-9._-]+[.](?P<extension>ss[tm]))$`);
-    static src_pth_pod_sst_or_ssm                   = ctRegex!(`^(?P<podpath>[/]?(?:[a-zA-Z0-9._-]+/)*)media/text/[a-z]{2}/(?P<filename>[a-zA-Z0-9][a-zA-Z0-9._-]*?[.]ss[tm])$`);
-    static src_pth_contents                         = ctRegex!(`^(?P<path>[/]?(?:[a-zA-Z0-9._-]+/)*)(?P<filename>[a-zA-Z0-9][a-zA-Z0-9._-]*)/pod[.]manifest$`);
-    static src_pth_zip                              = ctRegex!(`^(?P<path>[/]?(?:[a-zA-Z0-9._-]+/)*)(?P<filename>[a-zA-Z0-9._-]+(?:[.]zip|[.]sisupod))$`);
-    static src_pth_types                            = ctRegex!(`^(?P<path>[/]?[a-zA-Z0-9._-]+/)*(?P<gotfile>(?P<filename>[a-zA-Z0-9._-]+[.]ss[tm])|(?P<filelist>[a-zA-Z0-9._-]+/pod[.]manifest)|(?P<filezip>[a-zA-Z0-9._-]+(?:[.]zip|[.]sisupod)))$`);
-    static src_fn                                   = ctRegex!(`^([/]?(?:[a-zA-Z0-9._-]+/)*)(?P<fn_src>(?P<fn_base>[a-zA-Z0-9._-]+)[.](?P<fn_src_suffix>ss[tm]))$`);
-    static src_fn_master                            = ctRegex!(`^(?P<path>/?(?:[a-zA-Z0-9._-]+/)*)(?P<filename>[a-zA-Z0-9._-]+[.]ssm)$`);
-    static src_fn_find_inserts                      = ctRegex!(`^(?P<path>/?(?:[a-zA-Z0-9._-]+/)*)(?P<filename>[a-zA-Z0-9._-]+[.]ss[im])$`);
+    static src_pth_sst_or_ssm                       = ctRegex!(`^(?P<path>[/]?(?:[a-zA-Z0-9._:~-]+/)*)(?P<filename>[a-zA-Z0-9._-]+[.](?P<extension>ss[tm]))$`);
+    static src_pth_pod_sst_or_ssm                   = ctRegex!(`^(?P<podpath>[/]?(?:[a-zA-Z0-9._:~-]+/)*)media/text/[a-z]{2}/(?P<filename>[a-zA-Z0-9][a-zA-Z0-9._-]*?[.]ss[tm])$`);
+    static src_pth_contents                         = ctRegex!(`^(?P<path>[/]?(?:[a-zA-Z0-9._:~-]+/)*)(?P<filename>[a-zA-Z0-9][a-zA-Z0-9._-]*)/pod[.]manifest$`);
+    static src_pth_zip                              = ctRegex!(`^(?P<path>[/]?(?:[a-zA-Z0-9._:~-]+/)*)(?P<filename>[a-zA-Z0-9._-]+(?:[.]zip|[.]sisupod))$`);
+    static src_pth_types                            = ctRegex!(`^(?P<path>[/]?[a-zA-Z0-9._:~-]+/)*(?P<gotfile>(?P<filename>[a-zA-Z0-9._-]+[.]ss[tm])|(?P<filelist>[a-zA-Z0-9._-]+/pod[.]manifest)|(?P<filezip>[a-zA-Z0-9._-]+(?:[.]zip|[.]sisupod)))$`);
+    static src_fn                                   = ctRegex!(`^([/]?(?:[a-zA-Z0-9._:~-]+/)*)(?P<fn_src>(?P<fn_base>[a-zA-Z0-9._-]+)[.](?P<fn_src_suffix>ss[tm]))$`);
+    static src_fn_master                            = ctRegex!(`^(?P<path>/?(?:[a-zA-Z0-9._:~-]+/)*)(?P<filename>[a-zA-Z0-9._-]+[.]ssm)$`);
+    static src_fn_find_inserts                      = ctRegex!(`^(?P<path>/?(?:[a-zA-Z0-9._:~-]+/)*)(?P<filename>[a-zA-Z0-9._-]+[.]ss[im])$`);
     static insert_src_fn_ssi_or_sst                 = ctRegex!(`^<<\s*(?P<path>[a-zA-Z0-9._-]+/)*(?P<filename>[a-zA-Z0-9._-]+[.]ss[ti])$`);
-    static src_base_parent_dir_name                 = ctRegex!(`[/](?P<dir>(?:[a-zA-Z0-9._-]+))(?:/media/text/[a-z]{2})$`); // formalizes dir structure
-    static src_formalised_file_path_parts           = ctRegex!(`(?P<pth>(?:[/a-zA-Z0-9._-]+?)(?P<dir>[a-zA-Z0-9._-]+))(?:/media/text/[a-z]{2})$`); // formalizes dir structure
+    static src_base_parent_dir_name                 = ctRegex!(`[/](?P<dir>(?:[a-zA-Z0-9._:~-]+))(?:/media/text/[a-z]{2})$`); // formalizes dir structure
+    static src_formalised_file_path_parts           = ctRegex!(`(?P<pth>(?:[/a-zA-Z0-9._:~-]+?)(?P<dir>[a-zA-Z0-9._:~-]+))(?:/media/text/[a-z]{2})$`); // formalizes dir structure
     /+ language codes +/
     auto language_code_and_filename                                    =
        ctRegex!("(?:^|[/])(am|bg|bn|br|ca|cs|cy|da|de|el|en|eo|es|et|eu|fi|fr|ga|gl|he|hi|hr|hy|ia|is|it|ja|ko|la|lo|lt|lv|ml|mr|nl|no|nn|oc|pl|pt|pt_BR|ro|ru|sa|se|sk|sl|sq|sr|sv|ta|te|th|tk|tr|uk|ur|vi|zh)/[A-Za-z0-9._-].+?[.](?:sst|ssm)$");
diff --git a/src/sisudoc/outputs/io_out/defaults.d b/src/sisudoc/outputs/io_out/defaults.d
index 73a9af1..0896be0 100644
--- a/src/sisudoc/outputs/io_out/defaults.d
+++ b/src/sisudoc/outputs/io_out/defaults.d
@@ -85,7 +85,7 @@ template InternalMarkup() {
     string tc_p                   = "┆";
     string img                    = "☼";
     string sep                    = "␣"; // "~";"␣"; // "~";
-    string uid_sep                = ":";
+    string uid_sep                = "~";
     string on_o  = "「";       string on_c  = "」";
     string mk_bullet               = "● ";
     static string indent_by_spaces_provided(int indent, string _indent_spaces ="░░") {
diff --git a/src/sisudoc/outputs/io_out/rgx.d b/src/sisudoc/outputs/io_out/rgx.d
index cd7a8da..145b19b 100644
--- a/src/sisudoc/outputs/io_out/rgx.d
+++ b/src/sisudoc/outputs/io_out/rgx.d
@@ -63,17 +63,17 @@ static template spineRgxOut() {
     static nbsp_char                                = ctRegex!(`░`, "mg");
     static nbsp_chars                               = ctRegex!(`[░]+`, "mg");
     static middle_dot                               = ctRegex!(`·`, "mg");
-    static src_pth_sst_or_ssm                       = ctRegex!(`^(?P<path>[/]?(?:[a-zA-Z0-9._-]+/)*)(?P<filename>[a-zA-Z0-9._-]+[.](?P<extension>ss[tm]))$`);
-    static src_pth_pod_sst_or_ssm                   = ctRegex!(`^(?P<podpath>[/]?(?:[a-zA-Z0-9._-]+/)*)media/text/[a-z]{2}/(?P<filename>[a-zA-Z0-9][a-zA-Z0-9._-]*?[.]ss[tm])$`);
-    static src_pth_contents                         = ctRegex!(`^(?P<path>[/]?(?:[a-zA-Z0-9._-]+/)*)(?P<filename>[a-zA-Z0-9][a-zA-Z0-9._-]*)/pod[.]manifest$`);
-    static src_pth_zip                              = ctRegex!(`^(?P<path>[/]?(?:[a-zA-Z0-9._-]+/)*)(?P<filename>[a-zA-Z0-9._-]+(?:[.]zip|[.]sisupod))$`);
-    static src_pth_types                            = ctRegex!(`^(?P<path>[/]?[a-zA-Z0-9._-]+/)*(?P<gotfile>(?P<filename>[a-zA-Z0-9._-]+[.]ss[tm])|(?P<filelist>[a-zA-Z0-9._-]+/pod[.]manifest)|(?P<filezip>[a-zA-Z0-9._-]+(?:[.]zip|[.]sisupod)))$`);
-    static src_fn                                   = ctRegex!(`^([/]?(?:[a-zA-Z0-9._-]+/)*)(?P<fn_src>(?P<fn_base>[a-zA-Z0-9._-]+)[.](?P<fn_src_suffix>ss[tm]))$`);
-    static src_fn_master                            = ctRegex!(`^(?P<path>/?(?:[a-zA-Z0-9._-]+/)*)(?P<filename>[a-zA-Z0-9._-]+[.]ssm)$`);
-    static src_fn_find_inserts                      = ctRegex!(`^(?P<path>/?(?:[a-zA-Z0-9._-]+/)*)(?P<filename>[a-zA-Z0-9._-]+[.]ss[im])$`);
+    static src_pth_sst_or_ssm                       = ctRegex!(`^(?P<path>[/]?(?:[a-zA-Z0-9._:~-]+/)*)(?P<filename>[a-zA-Z0-9._-]+[.](?P<extension>ss[tm]))$`);
+    static src_pth_pod_sst_or_ssm                   = ctRegex!(`^(?P<podpath>[/]?(?:[a-zA-Z0-9._:~-]+/)*)media/text/[a-z]{2}/(?P<filename>[a-zA-Z0-9][a-zA-Z0-9._-]*?[.]ss[tm])$`);
+    static src_pth_contents                         = ctRegex!(`^(?P<path>[/]?(?:[a-zA-Z0-9._:~-]+/)*)(?P<filename>[a-zA-Z0-9][a-zA-Z0-9._-]*)/pod[.]manifest$`);
+    static src_pth_zip                              = ctRegex!(`^(?P<path>[/]?(?:[a-zA-Z0-9._:~-]+/)*)(?P<filename>[a-zA-Z0-9._-]+(?:[.]zip|[.]sisupod))$`);
+    static src_pth_types                            = ctRegex!(`^(?P<path>[/]?[a-zA-Z0-9._:~-]+/)*(?P<gotfile>(?P<filename>[a-zA-Z0-9._-]+[.]ss[tm])|(?P<filelist>[a-zA-Z0-9._-]+/pod[.]manifest)|(?P<filezip>[a-zA-Z0-9._-]+(?:[.]zip|[.]sisupod)))$`);
+    static src_fn                                   = ctRegex!(`^([/]?(?:[a-zA-Z0-9._:~-]+/)*)(?P<fn_src>(?P<fn_base>[a-zA-Z0-9._-]+)[.](?P<fn_src_suffix>ss[tm]))$`);
+    static src_fn_master                            = ctRegex!(`^(?P<path>/?(?:[a-zA-Z0-9._:~-]+/)*)(?P<filename>[a-zA-Z0-9._-]+[.]ssm)$`);
+    static src_fn_find_inserts                      = ctRegex!(`^(?P<path>/?(?:[a-zA-Z0-9._:~-]+/)*)(?P<filename>[a-zA-Z0-9._-]+[.]ss[im])$`);
     static insert_src_fn_ssi_or_sst                 = ctRegex!(`^<<\s*(?P<path>[a-zA-Z0-9._-]+/)*(?P<filename>[a-zA-Z0-9._-]+[.]ss[ti])$`);
-    static src_base_parent_dir_name                 = ctRegex!(`[/](?P<dir>(?:[a-zA-Z0-9._-]+))(?:/media/text/[a-z]{2})$`); // formalizes dir structure
-    static src_formalised_file_path_parts           = ctRegex!(`(?P<pth>(?:[/a-zA-Z0-9._-]+?)(?P<dir>[a-zA-Z0-9._-]+))(?:/media/text/[a-z]{2})$`); // formalizes dir structure
+    static src_base_parent_dir_name                 = ctRegex!(`[/](?P<dir>(?:[a-zA-Z0-9._:~-]+))(?:/media/text/[a-z]{2})$`); // formalizes dir structure
+    static src_formalised_file_path_parts           = ctRegex!(`(?P<pth>(?:[/a-zA-Z0-9._:~-]+?)(?P<dir>[a-zA-Z0-9._:~-]+))(?:/media/text/[a-z]{2})$`); // formalizes dir structure
     /+ line breaks +/
     static br_empty_line                            = ctRegex!(`\n[ ]*\n`, "mg");
     static br_linebreaks_newlines                   = ctRegex!(`[\n┘┙]`, "mg");