implement parsing human-readable names from URLs

Based off of commit 257b768436a0e8ab7887f9b790c5b92a7fe51ef5

Upstream-PR: https://github.com/NixOS/nix/pull/8678
Co-authored-by: Felix Uhl <felix.uhl@outlook.com>
Change-Id: Idcb7f6191ca3310ef9dc854197f7798260c3f71d

1 files changed, 59 insertions, 0 deletions

diff --git a/src/libutil/url-name.cc b/src/libutil/url-name.cc
new file mode 100644
index 000000000..6ef58c80a
--- /dev/null
+++ b/src/libutil/url-name.cc
@@ -0,0 +1,59 @@
+#include <iostream>
+#include <regex>
+
+#include "url-name.hh"
+
+namespace nix {
+
+static std::string const attributeNamePattern("[a-z0-9_-]+");
+static std::regex const lastAttributeRegex("(?:" + attributeNamePattern + "\\.)*(?!default)(" + attributeNamePattern +")(\\^.*)?");
+static std::string const pathSegmentPattern("[a-zA-Z0-9_-]+");
+static std::regex const lastPathSegmentRegex(".*/(" + pathSegmentPattern +")");
+static std::regex const secondPathSegmentRegex("(?:" + pathSegmentPattern + ")/(" + pathSegmentPattern +")(?:/.*)?");
+static std::regex const gitProviderRegex("github|gitlab|sourcehut");
+static std::regex const gitSchemeRegex("git($|\\+.*)");
+static std::regex const defaultOutputRegex(".*\\.default($|\\^.*)");
+
+std::optional<std::string> getNameFromURL(ParsedURL const & url)
+{
+    std::smatch match;
+
+    /* If there is a dir= argument, use its value */
+    if (url.query.count("dir") > 0) {
+        return url.query.at("dir");
+    }
+
+    /* If the fragment isn't a "default" and contains two attribute elements, use the last one */
+    if (std::regex_match(url.fragment, match, lastAttributeRegex)) {
+        return match.str(1);
+    }
+
+    /* If this is a github/gitlab/sourcehut flake, use the repo name */
+    if (
+        std::regex_match(url.scheme, gitProviderRegex)
+        && std::regex_match(url.path, match, secondPathSegmentRegex)
+    ) {
+        return match.str(1);
+    }
+
+    /* If it is a regular git flake, use the directory name */
+    if (
+        std::regex_match(url.scheme, gitSchemeRegex)
+        && std::regex_match(url.path, match, lastPathSegmentRegex)
+    ) {
+        return match.str(1);
+    }
+
+    /* If everything failed but there is a non-default fragment, use it in full */
+    if (!url.fragment.empty() && !std::regex_match(url.fragment, defaultOutputRegex))
+        return url.fragment;
+
+    /* If there is no fragment, take the last element of the path */
+    if (std::regex_match(url.path, match, lastPathSegmentRegex))
+        return match.str(1);
+
+    /* If even that didn't work, the URL does not contain enough info to determine a useful name */
+    return {};
+}
+
+}