[tracker-miners/wip/carlosg/stable-content-urns: 6/8] libtracker-miners-common: Add API to get stable URNs for file content

[Carlos Garnacho <carlosg src gnome org>]

commit 88f1be1e1b28c3bf7454ffe051b468bc38f1d3e6
Author: Carlos Garnacho <carlosg gnome org>
Date:   Wed Dec 15 02:11:21 2021 +0100

    libtracker-miners-common: Add API to get stable URNs for file content
    
    This helper function works on top of G_FILE_ATTRIBUTE_ID_FILE which
    based on the filesystem ID and inode. This shares the same lifetime
    expectancies we have about our own URNs:
    
    - It is unique system-wide.
    - It is persistent as long as there are no file content changes
      (e.g. persists on attribute updates).
    - It is persistent across file moves/renames too.
    
    And extends the benefits a bit:
    
    - It is persistent across reindexes.
    - It is a stat() away, no need to insert a blank node and query for its
      name.
    
    Add this piece of API that allows to generate one of these new
    stable URNs for file content. Optionally, a suffix can be added,
    for the cases where there will be multiple content entities for a
    file data object (e.g. flac).

 src/libtracker-miners-common/tracker-file-utils.c | 32 +++++++++++++++++++++++
 src/libtracker-miners-common/tracker-file-utils.h |  3 +++
 2 files changed, 35 insertions(+)
---
diff --git a/src/libtracker-miners-common/tracker-file-utils.c 
b/src/libtracker-miners-common/tracker-file-utils.c
index 778df49aa..78064e714 100644
--- a/src/libtracker-miners-common/tracker-file-utils.c
+++ b/src/libtracker-miners-common/tracker-file-utils.c
@@ -720,3 +720,35 @@ tracker_filename_casecmp_without_extension (const gchar *a,
 
        return g_ascii_strncasecmp (a, b, len_a) == 0;
 }
+
+gchar *
+tracker_file_get_content_identifier (GFile       *file,
+                                     GFileInfo   *info,
+                                     const gchar *suffix)
+{
+       const gchar *id;
+       gchar *str;
+
+       if (info) {
+               g_object_ref (info);
+       } else {
+               info = g_file_query_info (file,
+                                         G_FILE_ATTRIBUTE_ID_FILE,
+                                         G_FILE_QUERY_INFO_NONE,
+                                         NULL,
+                                         NULL);
+               if (!info)
+                       return NULL;
+       }
+
+       id = g_file_info_get_attribute_string (info, G_FILE_ATTRIBUTE_ID_FILE);
+
+       if (suffix)
+               str = g_strconcat ("urn:fileid:", id, "/", suffix, NULL);
+       else
+               str = g_strconcat ("urn:fileid:", id, NULL);
+
+       g_object_unref (info);
+
+       return str;
+}
diff --git a/src/libtracker-miners-common/tracker-file-utils.h 
b/src/libtracker-miners-common/tracker-file-utils.h
index fb4b200f2..f05535a41 100644
--- a/src/libtracker-miners-common/tracker-file-utils.h
+++ b/src/libtracker-miners-common/tracker-file-utils.h
@@ -44,6 +44,9 @@ gboolean tracker_file_is_locked                             (GFile       *file);
 gboolean tracker_file_is_hidden                             (GFile       *file);
 gint     tracker_file_cmp                                   (GFile       *file_a,
                                                              GFile       *file_b);
+gchar *  tracker_file_get_content_identifier                (GFile       *file,
+                                                             GFileInfo   *info,
+                                                             const gchar *suffix);
 
 /* Path utils */
 gboolean tracker_path_is_in_path                            (const gchar *path,