[epiphany/gnome-40] embed: Only lowercase search URI's hostname when we know it's an URI

[Michael Catanzaro <mcatanzaro src gnome org>]

commit 12520678cf546e9347b34c83f509f9c1a5f10c39
Author: vanadiae <vanadiae35 gmail com>
Date:   Fri Jul 16 21:05:05 2021 +0200

    embed: Only lowercase search URI's hostname when we know it's an URI
    
    Currently if doing a search using a bang (e.g. "!ddg GNOME") the whole search
    is lowercased. This is unexpected as one might want to include the correct
    caps so that it lands on the right page straight away, without needing to
    go through the search results page. This is the case for example if searching
    "!wt Katze" (with the wiktionary), where it'll land on a page saying that
    the "katze" page doesn't exist but instead there is the Katze page (in german
    caps at the beginning of words is important for nouns), even though "Katze" was
    already what was searched in Epiphany's search bar.
    
    So this was a bug where it wanted to lowercase only the hostname part (like
    GOOgle.com => google.com) but did it before it checked and processed the bang
    search, which isn't a proper URI so it assumes the hostname is the whole string
    and lowercases it.
    
    Part-of: <https://gitlab.gnome.org/GNOME/epiphany/-/merge_requests/988>
    
    
    (cherry picked from commit db602b13f35822eb409c3b32f8c8a7d59a7da251)

 embed/ephy-embed-utils.c | 61 ++++++++++++++++++++++++------------------------
 1 file changed, 30 insertions(+), 31 deletions(-)
---
diff --git a/embed/ephy-embed-utils.c b/embed/ephy-embed-utils.c
index 59c9e05c8..4e90a9346 100644
--- a/embed/ephy-embed-utils.c
+++ b/embed/ephy-embed-utils.c
@@ -260,23 +260,46 @@ ephy_embed_utils_address_is_valid (const char *address)
   return retval;
 }
 
+static char *
+ensure_host_name_is_lowercase (const char *address)
+{
+  g_autofree gchar *host = ephy_string_get_host_name (address);
+  g_autofree gchar *lowercase_host = NULL;
+
+  if (!host)
+    return g_strdup (address);
+
+  lowercase_host = g_utf8_strdown (host, -1);
+
+  if (strcmp (host, lowercase_host) != 0)
+    return ephy_string_find_and_replace (address, host, lowercase_host);
+  else
+    return g_strdup (address);
+}
+
 char *
-ephy_embed_utils_normalize_address (const char *address)
+ephy_embed_utils_normalize_address (const char *input_address)
 {
   char *effective_address = NULL;
+  g_autofree gchar *address = NULL;
 
-  g_assert (address);
-
-  if (is_bang_search (address)) {
+  g_assert (input_address);
+  /* We don't want to lowercase the host name if it's a bang search, as it's not a URI.
+   * It would otherwise lowercase the entire search string, bang included, which is not
+   * what we want. So use input_address directly.
+   */
+  if (is_bang_search (input_address)) {
     EphyEmbedShell *shell;
     EphySearchEngineManager *search_engine_manager;
 
     shell = ephy_embed_shell_get_default ();
     search_engine_manager = ephy_embed_shell_get_search_engine_manager (shell);
     return ephy_search_engine_manager_parse_bang_search (search_engine_manager,
-                                                         address);
+                                                         input_address);
   }
 
+  address = ensure_host_name_is_lowercase (input_address);
+
   if (ephy_embed_utils_address_is_existing_absolute_filename (address))
     return g_strconcat ("file://", address, NULL);
 
@@ -337,35 +360,11 @@ ephy_embed_utils_autosearch_address (const char *search_key)
   return effective_address;
 }
 
-static char *
-ensure_host_name_is_lowercase (const char *address)
-{
-  g_autofree gchar *host = ephy_string_get_host_name (address);
-  g_autofree gchar *lowercase_host = NULL;
-  char *ret = NULL;
-
-  if (host == NULL) {
-    return g_strdup (address);
-  }
-
-  lowercase_host = g_utf8_strdown (host, -1);
-
-  if (strcmp (host, lowercase_host) != 0) {
-    ret = ephy_string_find_and_replace (address, host, lowercase_host);
-  } else {
-    ret = g_strdup (address);
-  }
-
-  return ret;
-}
-
 char *
 ephy_embed_utils_normalize_or_autosearch_address (const char *address)
 {
-  g_autofree gchar *lower_case_address = ensure_host_name_is_lowercase (address);
-
-  if (ephy_embed_utils_address_is_valid (lower_case_address))
-    return ephy_embed_utils_normalize_address (lower_case_address);
+  if (ephy_embed_utils_address_is_valid (address))
+    return ephy_embed_utils_normalize_address (address);
   else
     return ephy_embed_utils_autosearch_address (address);
 }